CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation

Contrastive Language-Image Pre-training (CLIP) exhibits strong zero-shot classification ability on various image-level tasks, leading to the research to adapt CLIP for pixel-level open-vocabulary semantic segmentation without additional training. The key is to improve spatial representation of image-level CLIP, such as replacing self-attention map at last layer with self-self attention map or vision foundation model based attention map. In this paper, we present a novel hierarchical framework, named CLIPer, that hierarchically improves spatial representation of CLIP. The proposed CLIPer includes an early-layer fusion module and a fine-grained compensation module. We observe that, the embeddings and attention maps at early layers can preserve spatial structural information. Inspired by this, we design the early-layer fusion module to generate segmentation map with better spatial coherence. Afterwards, we employ a fine-grained compensation module to compensate the local details using the self-attention maps of diffusion model. We conduct the experiments on seven segmentation datasets. Our proposed CLIPer achieves the state-of-the-art performance on these datasets. For instance, using ViT-L, CLIPer has the mIoU of 69.8% and 43.3% on VOC and COCO Object, outperforming ProxyCLIP by 9.2% and 4.1% respectively.

Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning

Vision Language Models (VLMs), pre-trained on large-scale image-text datasets, enable zero-shot predictions for unseen data but may underperform on specific unseen tasks. Continual learning (CL) can help VLMs effectively adapt to new data distributions without joint training, but faces challenges of catastrophic forgetting and generalization forgetting. Although significant progress has been achieved by distillation-based methods, they exhibit two severe limitations. One is the popularly adopted single-teacher paradigm fails to impart comprehensive knowledge, The other is the existing methods inadequately leverage the multimodal information in the original training dataset, instead they rely on additional data for distillation, which increases computational and storage overhead. To mitigate both limitations, by drawing on Knowledge Integration Theory (KIT), we propose a Multi-Stage Knowledge Integration network (MulKI) to emulate the human learning process in distillation methods. MulKI achieves this through four stages, including Eliciting Ideas, Adding New Ideas, Distinguishing Ideas, and Making Connections. During the four stages, we first leverage prototypes to align across modalities, eliciting cross-modal knowledge, then adding new knowledge by constructing fine-grained intra- and inter-modality relationships with prototypes. After that, knowledge from two teacher models is adaptively distinguished and re-weighted. Finally, we connect between models from intra- and inter-task, integrating preceding and new knowledge. Our method demonstrates significant improvements in maintaining zero-shot capabilities while supporting continual learning across diverse downstream tasks, showcasing its potential in adapting VLMs to evolving data distributions.

A Fresh Look at Generalized Category Discovery through Non-negative Matrix Factorization

Generalized Category Discovery (GCD) aims to classify both base and novel images using labeled base data. However, current approaches inadequately address the intrinsic optimization of the co-occurrence matrix $\bar{A}$ based on cosine similarity, failing to achieve zero base-novel regions and adequate sparsity in base and novel domains. To address these deficiencies, we propose a Non-Negative Generalized Category Discovery (NN-GCD) framework. It employs Symmetric Non-negative Matrix Factorization (SNMF) as a mathematical medium to prove the equivalence of optimal K-means with optimal SNMF, and the equivalence of SNMF solver with non-negative contrastive learning (NCL) optimization. Utilizing these theoretical equivalences, it reframes the optimization of $\bar{A}$ and K-means clustering as an NCL optimization problem. Moreover, to satisfy the non-negative constraints and make a GCD model converge to a near-optimal region, we propose a GELU activation function and an NMF NCE loss. To transition $\bar{A}$ from a suboptimal state to the desired $\bar{A}^*$, we introduce a hybrid sparse regularization approach to impose sparsity constraints. Experimental results show NN-GCD outperforms state-of-the-art methods on GCD benchmarks, achieving an average accuracy of 66.1\% on the Semantic Shift Benchmark, surpassing prior counterparts by 4.7\%.

iSeg: An Iterative Refinement-based Framework for Training-free Segmentation

Stable diffusion has demonstrated strong image synthesis ability to given text descriptions, suggesting it to contain strong semantic clue for grouping objects. Inspired by this, researchers have explored employing stable diffusion for trainingfree segmentation. Most existing approaches either simply employ cross-attention map or refine it by self-attention map, to generate segmentation masks. We believe that iterative refinement with self-attention map would lead to better results. However, we mpirically demonstrate that such a refinement is sub-optimal likely due to the self-attention map containing irrelevant global information which hampers accurately refining cross-attention map with multiple iterations. To address this, we propose an iterative refinement framework for training-free segmentation, named iSeg, having an entropy-reduced self-attention module which utilizes a gradient descent scheme to reduce the entropy of self-attention map, thereby suppressing the weak responses corresponding to irrelevant global information. Leveraging the entropy-reduced self-attention module, our iSeg stably improves refined crossattention map with iterative refinement. Further, we design a category-enhanced cross-attention module to generate accurate cross-attention map, providing a better initial input for iterative refinement. Extensive experiments across different datasets and diverse segmentation tasks reveal the merits of proposed contributions, leading to promising performance on diverse segmentation tasks. For unsupervised semantic segmentation on Cityscapes, our iSeg achieves an absolute gain of 3.8% in terms of mIoU compared to the best existing training-free approach in literature. Moreover, our proposed iSeg can support segmentation with different kind of images and interactions.

Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective

Parameter-efficient fine-tuning for continual learning (PEFT-CL) has shown promise in adapting pre-trained models to sequential tasks while mitigating catastrophic forgetting problem. However, understanding the mechanisms that dictate continual performance in this paradigm remains elusive. To tackle this complexity, we undertake a rigorous analysis of PEFT-CL dynamics to derive relevant metrics for continual scenarios using Neural Tangent Kernel (NTK) theory. With the aid of NTK as a mathematical analysis tool, we recast the challenge of test-time forgetting into the quantifiable generalization gaps during training, identifying three key factors that influence these gaps and the performance of PEFT-CL: training sample size, task-level feature orthogonality, and regularization. To address these challenges, we introduce NTK-CL, a novel framework that eliminates task-specific parameter storage while adaptively generating task-relevant features. Aligning with theoretical guidance, NTK-CL triples the feature representation of each sample, theoretically and empirically reducing the magnitude of both task-interplay and task-specific generalization gaps. Grounded in NTK analysis, our approach imposes an adaptive exponential moving average mechanism and constraints on task-level feature orthogonality, maintaining intra-task NTK forms while attenuating inter-task NTK forms. Ultimately, by fine-tuning optimizable parameters with appropriate regularization, NTK-CL achieves state-of-the-art performance on established PEFT-CL benchmarks. This work provides a theoretical foundation for understanding and improving PEFT-CL models, offering insights into the interplay between feature representation, task orthogonality, and generalization, contributing to the development of more efficient continual learning systems.

Raformer: Redundancy-Aware Transformer for Video Wire Inpainting

Video Wire Inpainting (VWI) is a prominent application in video inpainting, aimed at flawlessly removing wires in films or TV series, offering significant time and labor savings compared to manual frame-by-frame removal. However, wire removal poses greater challenges due to the wires being longer and slimmer than objects typically targeted in general video inpainting tasks, and often intersecting with people and background objects irregularly, which adds complexity to the inpainting process. Recognizing the limitations posed by existing video wire datasets, which are characterized by their small size, poor quality, and limited variety of scenes, we introduce a new VWI dataset with a novel mask generation strategy, namely Wire Removal Video Dataset 2 (WRV2) and Pseudo Wire-Shaped (PWS) Masks. WRV2 dataset comprises over 4,000 videos with an average length of 80 frames, designed to facilitate the development and efficacy of inpainting models. Building upon this, our research proposes the Redundancy-Aware Transformer (Raformer) method that addresses the unique challenges of wire removal in video inpainting. Unlike conventional approaches that indiscriminately process all frame patches, Raformer employs a novel strategy to selectively bypass redundant parts, such as static background segments devoid of valuable information for inpainting. At the core of Raformer is the Redundancy-Aware Attention (RAA) module, which isolates and accentuates essential content through a coarse-grained, window-based attention mechanism. This is complemented by a Soft Feature Alignment (SFA) module, which refines these features and achieves end-to-end feature alignment. Extensive experiments on both the traditional video inpainting datasets and our proposed WRV2 dataset demonstrate that Raformer outperforms other state-of-the-art methods.

Implicit and Explicit Language Guidance for Diffusion-based Visual Perception

Text-to-image diffusion models have shown powerful ability on conditional image synthesis. With large-scale vision-language pre-training, diffusion models are able to generate high-quality images with rich texture and reasonable structure under different text prompts. However, it is an open problem to adapt the pre-trained diffusion model for visual perception. In this paper, we propose an implicit and explicit language guidance framework for diffusion-based perception, named IEDP. Our IEDP comprises of an implicit language guidance branch and an explicit language guidance branch. The implicit branch employs frozen CLIP image encoder to directly generate implicit text embeddings that are fed to diffusion model, without using explicit text prompts. The explicit branch utilizes the ground-truth labels of corresponding images as text prompts to condition feature extraction of diffusion model. During training, we jointly train diffusion model by sharing the model weights of these two branches. As a result, implicit and explicit branches can jointly guide feature learning. During inference, we only employ implicit branch for final prediction, which does not require any ground-truth labels. Experiments are performed on two typical perception tasks, including semantic segmentation and depth estimation. Our IEDP achieves promising performance on both tasks. For semantic segmentation, our IEDP has the mIoU score of 55.9% on AD20K validation set, which outperforms the baseline method VPD by 2.2%. For depth estimation, our IEDP outperforms the baseline method VPD with a relative gain of 10.2%.

The state-of-the-art in Cardiac MRI Reconstruction: Results of the CMRxRecon Challenge in MICCAI 2023

Cardiac MRI, crucial for evaluating heart structure and function, faces limitations like slow imaging and motion artifacts. Undersampling reconstruction, especially data-driven algorithms, has emerged as a promising solution to accelerate scans and enhance imaging performance using highly under-sampled data. Nevertheless, the scarcity of publicly available cardiac k-space datasets and evaluation platform hinder the development of data-driven reconstruction algorithms. To address this issue, we organized the Cardiac MRI Reconstruction Challenge (CMRxRecon) in 2023, in collaboration with the 26th International Conference on MICCAI. CMRxRecon presented an extensive k-space dataset comprising cine and mapping raw data, accompanied by detailed annotations of cardiac anatomical structures. With overwhelming participation, the challenge attracted more than 285 teams and over 600 participants. Among them, 22 teams successfully submitted Docker containers for the testing phase, with 7 teams submitted for both cine and mapping tasks. All teams use deep learning based approaches, indicating that deep learning has predominately become a promising solution for the problem. The first-place winner of both tasks utilizes the E2E-VarNet architecture as backbones. In contrast, U-Net is still the most popular backbone for both multi-coil and single-coil reconstructions. This paper provides a comprehensive overview of the challenge design, presents a summary of the submitted results, reviews the employed methods, and offers an in-depth discussion that aims to inspire future advancements in cardiac MRI reconstruction models. The summary emphasizes the effective strategies observed in Cardiac MRI reconstruction, including backbone architecture, loss function, pre-processing techniques, physical modeling, and model complexity, thereby providing valuable insights for further developments in this field.

NTK-Guided Few-Shot Class Incremental Learning

While anti-amnesia FSCIL learners often excel in incremental sessions, they tend to prioritize mitigating knowledge attrition over harnessing the model's potential for knowledge acquisition. In this paper, we delve into the foundations of model generalization in FSCIL through the lens of the Neural Tangent Kernel (NTK). Our primary design focus revolves around ensuring optimal NTK convergence and NTK-related generalization error, serving as the theoretical bedrock for exceptional generalization. To attain globally optimal NTK convergence, we employ a meta-learning mechanism grounded in mathematical principles to guide the optimization process within an expanded network. Furthermore, to reduce the NTK-related generalization error, we commence from the foundational level, optimizing the relevant factors constituting its generalization loss. Specifically, we initiate self-supervised pre-training on the base session to shape the initial network weights. Then they are carefully refined through curricular alignment, followed by the application of dual NTK regularization tailored specifically for both convolutional and linear layers. Through the combined effects of these measures, our network acquires robust NTK properties, significantly enhancing its foundational generalization. On popular FSCIL benchmark datasets, our NTK-FSCIL surpasses contemporary state-of-the-art approaches, elevating end-session accuracy by 2.9% to 8.7%.

CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance Segmentation

Open-vocabulary video instance segmentation strives to segment and track instances belonging to an open set of categories in a video. The vision-language model Contrastive Language-Image Pre-training (CLIP) has shown strong zero-shot classification ability in image-level open-vocabulary task. In this paper, we propose a simple encoder-decoder network, called CLIP-VIS, to adapt CLIP for open-vocabulary video instance segmentation. Our CLIP-VIS adopts frozen CLIP image encoder and introduces three modules, including class-agnostic mask generation, temporal topK-enhanced matching, and weighted open-vocabulary classification. Given a set of initial queries, class-agnostic mask generation employs a transformer decoder to predict query masks and corresponding object scores and mask IoU scores. Then, temporal topK-enhanced matching performs query matching across frames by using K mostly matched frames. Finally, weighted open-vocabulary classification first generates query visual features with mask pooling, and second performs weighted classification using object scores and mask IoU scores. Our CLIP-VIS does not require the annotations of instance categories and identities. The experiments are performed on various video instance segmentation datasets, which demonstrate the effectiveness of our proposed method, especially on novel categories. When using ConvNeXt-B as backbone, our CLIP-VIS achieves the AP and APn scores of 32.1% and 40.3% on validation set of LV-VIS dataset, which outperforms OV2Seg by 11.0% and 24.0% respectively. We will release the source code and models at https://github.com/zwq456/CLIP-VIS.git.