Abstract:A plethora of text-guided image editing methods has recently been developed by leveraging the impressive capabilities of large-scale diffusion-based generative models especially Stable Diffusion. Despite the success of diffusion models in producing high-quality images, their application to small object generation has been limited due to difficulties in aligning cross-modal attention maps between text and these objects. Our approach offers a training-free method that significantly mitigates this alignment issue with local and global attention guidance , enhancing the model's ability to accurately render small objects in accordance with textual descriptions. We detail the methodology in our approach, emphasizing its divergence from traditional generation techniques and highlighting its advantages. What's more important is that we also provide~\textit{SOEBench} (Small Object Editing), a standardized benchmark for quantitatively evaluating text-based small object generation collected from \textit{MSCOCO} and \textit{OpenImage}. Preliminary results demonstrate the effectiveness of our method, showing marked improvements in the fidelity and accuracy of small object generation compared to existing models. This advancement not only contributes to the field of AI and computer vision but also opens up new possibilities for applications in various industries where precise image generation is critical. We will release our dataset on our project page: \href{https://soebench.github.io/}{https://soebench.github.io/}.
Abstract:In the domain of language-based fashion image retrieval, pinpointing the desired fashion item using both a reference image and its accompanying textual description is an intriguing challenge. Existing approaches lean heavily on static fusion techniques, intertwining image and text. Despite their commendable advancements, these approaches are still limited by a deficiency in flexibility. In response, we propose a Self-distilled Dynamic Fusion Network to compose the multi-granularity features dynamically by considering the consistency of routing path and modality-specific information simultaneously. Two new modules are included in our proposed method: (1) Dynamic Fusion Network with Modality Specific Routers. The dynamic network enables a flexible determination of the routing for each reference image and modification text, taking into account their distinct semantics and distributions. (2) Self Path Distillation Loss. A stable path decision for queries benefits the optimization of feature extraction as well as routing, and we approach this by progressively refine the path decision with previous path information. Extensive experiments demonstrate the effectiveness of our proposed model compared to existing methods.
Abstract:Point cloud analysis has seen substantial advancements due to deep learning, although previous Transformer-based methods excel at modeling long-range dependencies on this task, their computational demands are substantial. Conversely, the Mamba offers greater efficiency but shows limited potential compared with Transformer-based methods. In this study, we introduce PoinTramba, a pioneering hybrid framework that synergies the analytical power of Transformer with the remarkable computational efficiency of Mamba for enhanced point cloud analysis. Specifically, our approach first segments point clouds into groups, where the Transformer meticulously captures intricate intra-group dependencies and produces group embeddings, whose inter-group relationships will be simultaneously and adeptly captured by efficient Mamba architecture, ensuring comprehensive analysis. Unlike previous Mamba approaches, we introduce a bi-directional importance-aware ordering (BIO) strategy to tackle the challenges of random ordering effects. This innovative strategy intelligently reorders group embeddings based on their calculated importance scores, significantly enhancing Mamba's performance and optimizing the overall analytical process. Our framework achieves a superior balance between computational efficiency and analytical performance by seamlessly integrating these advanced techniques, marking a substantial leap forward in point cloud analysis. Extensive experiments on datasets such as ScanObjectNN, ModelNet40, and ShapeNetPart demonstrate the effectiveness of our approach, establishing a new state-of-the-art analysis benchmark on point cloud recognition. For the first time, this paradigm leverages the combined strengths of both Transformer and Mamba architectures, facilitating a new standard in the field. The code is available at https://github.com/xiaoyao3302/PoinTramba.
Abstract:In this paper, we delve into a new task known as small object editing (SOE), which focuses on text-based image inpainting within a constrained, small-sized area. Despite the remarkable success have been achieved by current image inpainting approaches, their application to the SOE task generally results in failure cases such as Object Missing, Text-Image Mismatch, and Distortion. These failures stem from the limited use of small-sized objects in training datasets and the downsampling operations employed by U-Net models, which hinders accurate generation. To overcome these challenges, we introduce a novel training-based approach, SOEDiff, aimed at enhancing the capability of baseline models like StableDiffusion in editing small-sized objects while minimizing training costs. Specifically, our method involves two key components: SO-LoRA, which efficiently fine-tunes low-rank matrices, and Cross-Scale Score Distillation loss, which leverages high-resolution predictions from the pre-trained teacher diffusion model. Our method presents significant improvements on the test dataset collected from MSCOCO and OpenImage, validating the effectiveness of our proposed method in small object editing. In particular, when comparing SOEDiff with SD-I model on the OpenImage-f dataset, we observe a 0.99 improvement in CLIP-Score and a reduction of 2.87 in FID. Our project page can be found in https://soediff.github.io/.
Abstract:Prompt learning has become the most effective paradigm for adapting large pre-trained vision-language models (VLMs) to downstream tasks. Recently, unsupervised prompt tuning methods, such as UPL and POUF, directly leverage pseudo-labels as supervisory information to fine-tune additional adaptation modules on unlabeled data. However, inaccurate pseudo labels easily misguide the tuning process and result in poor representation capabilities. In light of this, we propose Training-Free Unsupervised Prompts (TFUP), which maximally preserves the inherent representation capabilities and enhances them with a residual connection to similarity-based prediction probabilities in a training-free and labeling-free manner. Specifically, we integrate both instance confidence and prototype scores to select representative samples, which are used to customize a reliable Feature Cache Model (FCM) for training-free inference. Then, we design a Multi-level Similarity Measure (MSM) that considers both feature-level and semantic-level similarities to calculate the distance between each test image and the cached sample as the weight of the corresponding cached label to generate similarity-based prediction probabilities. In this way, TFUP achieves surprising performance, even surpassing the training-base method on multiple classification datasets. Based on our TFUP, we propose a training-based approach (TFUP-T) to further boost the adaptation performance. In addition to the standard cross-entropy loss, TFUP-T adopts an additional marginal distribution entropy loss to constrain the model from a global perspective. Our TFUP-T achieves new state-of-the-art classification performance compared to unsupervised and few-shot adaptation approaches on multiple benchmarks. In particular, TFUP-T improves the classification accuracy of POUF by 3.3% on the most challenging Domain-Net dataset.
Abstract:Unsupervised domain adaptation is a critical challenge in the field of point cloud analysis, as models trained on one set of data often struggle to perform well in new scenarios due to domain shifts. Previous works tackle the problem by using adversarial training or self-supervised learning for feature extractor adaptation, but ensuring that features extracted from the target domain can be distinguished by the source-supervised classifier remains challenging. In this work, we propose a novel approach called progressive target-styled feature augmentation (PTSFA). Unlike previous works that focus on feature extractor adaptation, our PTSFA approach focuses on classifier adaptation. It aims to empower the classifier to recognize target-styled source features and progressively adapt to the target domain. To enhance the reliability of predictions within the PTSFA framework and encourage discriminative feature extraction, we further introduce a new intermediate domain approaching (IDA) strategy. We validate our method on the benchmark datasets, where our method achieves new state-of-the-art performance. Our code is available at https://github.com/xiaoyao3302/PTSFA.
Abstract:The aim of latent variable disentanglement is to infer the multiple informative latent representations that lie behind a data generation process and is a key factor in controllable data generation. In this paper, we propose a deep neural network-based self-supervised learning method to infer the disentangled rhythmic and harmonic representations behind music audio generation. We train a variational autoencoder that generates an audio mel-spectrogram from two latent features representing the rhythmic and harmonic content. In the training phase, the variational autoencoder is trained to reconstruct the input mel-spectrogram given its pitch-shifted version. At each forward computation in the training phase, a vector rotation operation is applied to one of the latent features, assuming that the dimensions of the feature vectors are related to pitch intervals. Therefore, in the trained variational autoencoder, the rotated latent feature represents the pitch-related information of the mel-spectrogram, and the unrotated latent feature represents the pitch-invariant information, i.e., the rhythmic content. The proposed method was evaluated using a predictor-based disentanglement metric on the learned features. Furthermore, we demonstrate its application to the automatic generation of music remixes.
Abstract:Panoptic Scene Graph Generation (PSG) parses objects and predicts their relationships (predicate) to connect human language and visual scenes. However, different language preferences of annotators and semantic overlaps between predicates lead to biased predicate annotations in the dataset, i.e. different predicates for same object pairs. Biased predicate annotations make PSG models struggle in constructing a clear decision plane among predicates, which greatly hinders the real application of PSG models. To address the intrinsic bias above, we propose a novel framework named ADTrans to adaptively transfer biased predicate annotations to informative and unified ones. To promise consistency and accuracy during the transfer process, we propose to measure the invariance of representations in each predicate class, and learn unbiased prototypes of predicates with different intensities. Meanwhile, we continuously measure the distribution changes between each presentation and its prototype, and constantly screen potential biased data. Finally, with the unbiased predicate-prototype representation embedding space, biased annotations are easily identified. Experiments show that ADTrans significantly improves the performance of benchmark models, achieving a new state-of-the-art performance, and shows great generalization and effectiveness on multiple datasets.
Abstract:Vision-based Bird's Eye View (BEV) representation is an emerging perception formulation for autonomous driving. The core challenge is to construct BEV space with multi-camera features, which is a one-to-many ill-posed problem. Diving into all previous BEV representation generation methods, we found that most of them fall into two types: modeling depths in image views or modeling heights in the BEV space, mostly in an implicit way. In this work, we propose to explicitly model heights in the BEV space, which needs no extra data like LiDAR and can fit arbitrary camera rigs and types compared to modeling depths. Theoretically, we give proof of the equivalence between height-based methods and depth-based methods. Considering the equivalence and some advantages of modeling heights, we propose HeightFormer, which models heights and uncertainties in a self-recursive way. Without any extra data, the proposed HeightFormer could estimate heights in BEV accurately. Benchmark results show that the performance of HeightFormer achieves SOTA compared with those camera-only methods.
Abstract:Given an untrimmed video and natural language query, video sentence grounding aims to localize the target temporal moment in the video. Existing methods mainly tackle this task by matching and aligning semantics of the descriptive sentence and video segments on a single temporal resolution, while neglecting the temporal consistency of video content in different resolutions. In this work, we propose a novel multi-resolution temporal video sentence grounding network: MRTNet, which consists of a multi-modal feature encoder, a Multi-Resolution Temporal (MRT) module, and a predictor module. MRT module is an encoder-decoder network, and output features in the decoder part are in conjunction with Transformers to predict the final start and end timestamps. Particularly, our MRT module is hot-pluggable, which means it can be seamlessly incorporated into any anchor-free models. Besides, we utilize a hybrid loss to supervise cross-modal features in MRT module for more accurate grounding in three scales: frame-level, clip-level and sequence-level. Extensive experiments on three prevalent datasets have shown the effectiveness of MRTNet.