Separable Mixture of Low-Rank Adaptation for Continual Visual Instruction Tuning

Visual instruction tuning (VIT) enables multimodal large language models (MLLMs) to effectively handle a wide range of vision tasks by framing them as language-based instructions. Building on this, continual visual instruction tuning (CVIT) extends the capability of MLLMs to incrementally learn new tasks, accommodating evolving functionalities. While prior work has advanced CVIT through the development of new benchmarks and approaches to mitigate catastrophic forgetting, these efforts largely follow traditional continual learning paradigms, neglecting the unique challenges specific to CVIT. We identify a dual form of catastrophic forgetting in CVIT, where MLLMs not only forget previously learned visual understanding but also experience a decline in instruction following abilities as they acquire new tasks. To address this, we introduce the Separable Mixture of Low-Rank Adaptation (SMoLoRA) framework, which employs separable routing through two distinct modules - one for visual understanding and another for instruction following. This dual-routing design enables specialized adaptation in both domains, preventing forgetting while improving performance. Furthermore, we propose a novel CVIT benchmark that goes beyond existing benchmarks by additionally evaluating a model's ability to generalize to unseen tasks and handle diverse instructions across various tasks. Extensive experiments demonstrate that SMoLoRA outperforms existing methods in mitigating dual forgetting, improving generalization to unseen tasks, and ensuring robustness in following diverse instructions.

Visual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Models

Knowledge editing aims to efficiently and cost-effectively correct inaccuracies and update outdated information. Recently, there has been growing interest in extending knowledge editing from Large Language Models (LLMs) to Multimodal Large Language Models (MLLMs), which integrate both textual and visual information, introducing additional editing complexities. Existing multimodal knowledge editing works primarily focus on text-oriented, coarse-grained scenarios, failing to address the unique challenges posed by multimodal contexts. In this paper, we propose a visual-oriented, fine-grained multimodal knowledge editing task that targets precise editing in images with multiple interacting entities. We introduce the Fine-Grained Visual Knowledge Editing (FGVEdit) benchmark to evaluate this task. Moreover, we propose a Multimodal Scope Classifier-based Knowledge Editor (MSCKE) framework. MSCKE leverages a multimodal scope classifier that integrates both visual and textual information to accurately identify and update knowledge related to specific entities within images. This approach ensures precise editing while preserving irrelevant information, overcoming the limitations of traditional text-only editing methods. Extensive experiments on the FGVEdit benchmark demonstrate that MSCKE outperforms existing methods, showcasing its effectiveness in solving the complex challenges of multimodal knowledge editing.

Learning Frequency-Aware Dynamic Transformers for All-In-One Image Restoration

This work aims to tackle the all-in-one image restoration task, which seeks to handle multiple types of degradation with a single model. The primary challenge is to extract degradation representations from the input degraded images and use them to guide the model's adaptation to specific degradation types. Recognizing that various degradations affect image content differently across frequency bands, we propose a new all-in-one image restoration approach from a frequency perspective, leveraging advanced vision transformers. Our method consists of two main components: a frequency-aware Degradation prior learning transformer (Dformer) and a degradation-adaptive Restoration transformer (Rformer). The Dformer captures the essential characteristics of various degradations by decomposing inputs into different frequency components. By understanding how degradations affect these frequency components, the Dformer learns robust priors that effectively guide the restoration process. The Rformer then employs a degradation-adaptive self-attention module to selectively focus on the most affected frequency components, guided by the learned degradation representations. Extensive experimental results demonstrate that our approach outperforms the existing methods on four representative restoration tasks, including denoising, deraining, dehazing and deblurring. Additionally, our method offers benefits for handling spatially variant degradations and unseen degradation levels.

Densely Distilling Cumulative Knowledge for Continual Learning

Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting. While knowledge distillation-based approaches exhibit notable success in preventing forgetting, we pinpoint a limitation in their ability to distill the cumulative knowledge of all the previous tasks. To remedy this, we propose Dense Knowledge Distillation (DKD). DKD uses a task pool to track the model's capabilities. It partitions the output logits of the model into dense groups, each corresponding to a task in the task pool. It then distills all tasks' knowledge using all groups. However, using all the groups can be computationally expensive, we also suggest random group selection in each optimization step. Moreover, we propose an adaptive weighting scheme, which balances the learning of new classes and the retention of old classes, based on the count and similarity of the classes. Our DKD outperforms recent state-of-the-art baselines across diverse benchmarks and scenarios. Empirical analysis underscores DKD's ability to enhance model stability, promote flatter minima for improved generalization, and remains robust across various memory budgets and task orders. Moreover, it seamlessly integrates with other CL methods to boost performance and proves versatile in offline scenarios like model compression.

DualMatch: Robust Semi-Supervised Learning with Dual-Level Interaction

Semi-supervised learning provides an expressive framework for exploiting unlabeled data when labels are insufficient. Previous semi-supervised learning methods typically match model predictions of different data-augmented views in a single-level interaction manner, which highly relies on the quality of pseudo-labels and results in semi-supervised learning not robust. In this paper, we propose a novel SSL method called DualMatch, in which the class prediction jointly invokes feature embedding in a dual-level interaction manner. DualMatch requires consistent regularizations for data augmentation, specifically, 1) ensuring that different augmented views are regulated with consistent class predictions, and 2) ensuring that different data of one class are regulated with similar feature embeddings. Extensive experiments demonstrate the effectiveness of DualMatch. In the standard SSL setting, the proposal achieves 9% error reduction compared with SOTA methods, even in a more challenging class-imbalanced setting, the proposal can still achieve 6% error reduction. Code is available at https://github.com/CWangAI/DualMatch

Training-free Object Counting with Prompts

This paper tackles the problem of object counting in images. Existing approaches rely on extensive training data with point annotations for each object, making data collection labor-intensive and time-consuming. To overcome this, we propose a training-free object counter that treats the counting task as a segmentation problem. Our approach leverages the Segment Anything Model (SAM), known for its high-quality masks and zero-shot segmentation capability. However, the vanilla mask generation method of SAM lacks class-specific information in the masks, resulting in inferior counting accuracy. To overcome this limitation, we introduce a prior-guided mask generation method that incorporates three types of priors into the segmentation process, enhancing efficiency and accuracy. Additionally, we tackle the issue of counting objects specified through free-form text by proposing a two-stage approach that combines reference object selection and prior-guided mask generation. Extensive experiments on standard datasets demonstrate the competitive performance of our training-free counter compared to learning-based approaches. This paper presents a promising solution for counting objects in various scenarios without the need for extensive data collection and model training. Code is available at https://github.com/shizenglin/training-free-object-counter.

Focus for Free in Density-Based Counting

This work considers supervised learning to count from images and their corresponding point annotations. Where density-based counting methods typically use the point annotations only to create Gaussian-density maps, which act as the supervision signal, the starting point of this work is that point annotations have counting potential beyond density map generation. We introduce two methods that repurpose the available point annotations to enhance counting performance. The first is a counting-specific augmentation that leverages point annotations to simulate occluded objects in both input and density images to enhance the network's robustness to occlusions. The second method, foreground distillation, generates foreground masks from the point annotations, from which we train an auxiliary network on images with blacked-out backgrounds. By doing so, it learns to extract foreground counting knowledge without interference from the background. These methods can be seamlessly integrated with existing counting advances and are adaptable to different loss functions. We demonstrate complementary effects of the approaches, allowing us to achieve robust counting results even in challenging scenarios such as background clutter, occlusion, and varying crowd densities. Our proposed approach achieves strong counting results on multiple datasets, including ShanghaiTech Part\_A and Part\_B, UCF\_QNRF, JHU-Crowd++, and NWPU-Crowd.

On the Robustness, Generalization, and Forgetting of Shape-Texture Debiased Continual Learning

Tremendous progress has been made in continual learning to maintain good performance on old tasks when learning new tasks by tackling the catastrophic forgetting problem of neural networks. This paper advances continual learning by further considering its out-of-distribution robustness, in response to the vulnerability of continually trained models to distribution shifts (e.g., due to data corruptions and domain shifts) in inference. To this end, we propose shape-texture debiased continual learning. The key idea is to learn generalizable and robust representations for each task with shape-texture debiased training. In order to transform standard continual learning to shape-texture debiased continual learning, we propose shape-texture debiased data generation and online shape-texture debiased self-distillation. Experiments on six datasets demonstrate the benefits of our approach in improving generalization and robustness, as well as reducing forgetting. Our analysis on the flatness of the loss landscape explains the advantages. Moreover, our approach can be easily combined with new advanced architectures such as vision transformer, and applied to more challenging scenarios such as exemplar-free continual learning.

Reason from Context with Self-supervised Learning

A tiny object in the sky cannot be an elephant. Context reasoning is critical in visual recognition, where current inputs need to be interpreted in the light of previous experience and knowledge. To date, research into contextual reasoning in visual recognition has largely proceeded with supervised learning methods. The question of whether contextual knowledge can be captured with self-supervised learning regimes remains under-explored. Here, we established a methodology for context-aware self-supervised learning. We proposed a novel Self-supervised Learning Method for Context Reasoning (SeCo), where the only inputs to SeCo are unlabeled images with multiple objects present in natural scenes. Similar to the distinction between fovea and periphery in human vision, SeCo processes self-proposed target object regions and their contexts separately, and then employs a learnable external memory for retrieving and updating context-relevant target information. To evaluate the contextual associations learned by the computational models, we introduced two evaluation protocols, lift-the-flap and object priming, addressing the problems of "what" and "where" in context reasoning. In both tasks, SeCo outperformed all state-of-the-art (SOTA) self-supervised learning methods by a significant margin. Our network analysis revealed that the external memory in SeCo learns to store prior contextual knowledge, facilitating target identity inference in lift-the-flap task. Moreover, we conducted psychophysics experiments and introduced a Human benchmark in Object Priming dataset (HOP). Our quantitative and qualitative results demonstrate that SeCo approximates human-level performance and exhibits human-like behavior. All our source code and data are publicly available here.

Social Fabric: Tubelet Compositions for Video Relation Detection

This paper strives to classify and detect the relationship between object tubelets appearing within a video as a <subject-predicate-object> triplet. Where existing works treat object proposals or tubelets as single entities and model their relations a posteriori, we propose to classify and detect predicates for pairs of object tubelets a priori. We also propose Social Fabric: an encoding that represents a pair of object tubelets as a composition of interaction primitives. These primitives are learned over all relations, resulting in a compact representation able to localize and classify relations from the pool of co-occurring object tubelets across all timespans in a video. The encoding enables our two-stage network. In the first stage, we train Social Fabric to suggest proposals that are likely interacting. We use the Social Fabric in the second stage to simultaneously fine-tune and predict predicate labels for the tubelets. Experiments demonstrate the benefit of early video relation modeling, our encoding and the two-stage architecture, leading to a new state-of-the-art on two benchmarks. We also show how the encoding enables query-by-primitive-example to search for spatio-temporal video relations. Code: https://github.com/shanshuo/Social-Fabric.