Data-Free Knowledge Distillation (DFKD) is a promising task to train high-performance small models to enhance actual deployment without relying on the original training data. Existing methods commonly avoid relying on private data by utilizing synthetic or sampled data. However, a long-overlooked issue is that the severe distribution shifts between their substitution and original data, which manifests as huge differences in the quality of images and class proportions. The harmful shifts are essentially the confounder that significantly causes performance bottlenecks. To tackle the issue, this paper proposes a novel perspective with causal inference to disentangle the student models from the impact of such shifts. By designing a customized causal graph, we first reveal the causalities among the variables in the DFKD task. Subsequently, we propose a Knowledge Distillation Causal Intervention (KDCI) framework based on the backdoor adjustment to de-confound the confounder. KDCI can be flexibly combined with most existing state-of-the-art baselines. Experiments in combination with six representative DFKD methods demonstrate the effectiveness of our KDCI, which can obviously help existing methods under almost all settings, \textit{e.g.}, improving the baseline by up to 15.54\% accuracy on the CIFAR-100 dataset.
In software evolution, resolving the emergent issues within GitHub repositories is a complex challenge that involves not only the incorporation of new code but also the maintenance of existing functionalities. Large Language Models (LLMs) have shown promise in code generation and understanding but face difficulties in code change, particularly at the repository level. To overcome these challenges, we empirically study the reason why LLMs mostly fail to resolve GitHub issues and analyze some impact factors. Motivated by the empirical findings, we propose a novel LLM-based Multi-Agent framework for GitHub Issue reSolution, MAGIS, consisting of four kinds of agents customized for the software evolution: Manager, Repository Custodian, Developer, and Quality Assurance Engineer agents. This framework leverages the collaboration of various agents in the planning and coding process to unlock the potential of LLMs to resolve GitHub issues. In experiments, we employ the SWE-bench benchmark to compare MAGIS with popular LLMs, including GPT-3.5, GPT-4, and Claude-2. MAGIS can resolve 13.94% GitHub issues, which significantly outperforms the baselines. Specifically, MAGIS achieves an eight-fold increase in resolved ratio over the direct application of GPT-4, the based LLM of our method. We also analyze the factors for improving GitHub issue resolution rates, such as line location, task allocation, etc.
Despite the substantial advancements in Vision-Language Pre-training (VLP) models, their susceptibility to adversarial attacks poses a significant challenge. Existing work rarely studies the transferability of attacks on VLP models, resulting in a substantial performance gap from white-box attacks. We observe that prior work overlooks the interaction mechanisms between modalities, which plays a crucial role in understanding the intricacies of VLP models. In response, we propose a novel attack, called Collaborative Multimodal Interaction Attack (CMI-Attack), leveraging modality interaction through embedding guidance and interaction enhancement. Specifically, attacking text at the embedding level while preserving semantics, as well as utilizing interaction image gradients to enhance constraints on perturbations of texts and images. Significantly, in the image-text retrieval task on Flickr30K dataset, CMI-Attack raises the transfer success rates from ALBEF to TCL, $\text{CLIP}_{\text{ViT}}$ and $\text{CLIP}_{\text{CNN}}$ by 8.11%-16.75% over state-of-the-art methods. Moreover, CMI-Attack also demonstrates superior performance in cross-task generalization scenarios. Our work addresses the underexplored realm of transfer attacks on VLP models, shedding light on the importance of modality interaction for enhanced adversarial robustness.
Visual object tracking aims to localize the target object of each frame based on its initial appearance in the first frame. Depending on the input modility, tracking tasks can be divided into RGB tracking and RGB+X (e.g. RGB+N, and RGB+D) tracking. Despite the different input modalities, the core aspect of tracking is the temporal matching. Based on this common ground, we present a general framework to unify various tracking tasks, termed as OneTracker. OneTracker first performs a large-scale pre-training on a RGB tracker called Foundation Tracker. This pretraining phase equips the Foundation Tracker with a stable ability to estimate the location of the target object. Then we regard other modality information as prompt and build Prompt Tracker upon Foundation Tracker. Through freezing the Foundation Tracker and only adjusting some additional trainable parameters, Prompt Tracker inhibits the strong localization ability from Foundation Tracker and achieves parameter-efficient finetuning on downstream RGB+X tracking tasks. To evaluate the effectiveness of our general framework OneTracker, which is consisted of Foundation Tracker and Prompt Tracker, we conduct extensive experiments on 6 popular tracking tasks across 11 benchmarks and our OneTracker outperforms other models and achieves state-of-the-art performance.
Contemporary Video Object Segmentation (VOS) approaches typically consist stages of feature extraction, matching, memory management, and multiple objects aggregation. Recent advanced models either employ a discrete modeling for these components in a sequential manner, or optimize a combined pipeline through substructure aggregation. However, these existing explicit staged approaches prevent the VOS framework from being optimized as a unified whole, leading to the limited capacity and suboptimal performance in tackling complex videos. In this paper, we propose OneVOS, a novel framework that unifies the core components of VOS with All-in-One Transformer. Specifically, to unify all aforementioned modules into a vision transformer, we model all the features of frames, masks and memory for multiple objects as transformer tokens, and integrally accomplish feature extraction, matching and memory management of multiple objects through the flexible attention mechanism. Furthermore, a Unidirectional Hybrid Attention is proposed through a double decoupling of the original attention operation, to rectify semantic errors and ambiguities of stored tokens in OneVOS framework. Finally, to alleviate the storage burden and expedite inference, we propose the Dynamic Token Selector, which unveils the working mechanism of OneVOS and naturally leads to a more efficient version of OneVOS. Extensive experiments demonstrate the superiority of OneVOS, achieving state-of-the-art performance across 7 datasets, particularly excelling in complex LVOS and MOSE datasets with 70.1% and 66.4% $J \& F$ scores, surpassing previous state-of-the-art methods by 4.2% and 7.0%, respectively. And our code will be available for reproducibility and further research.
Video Object Segmentation (VOS) task aims to segment objects in videos. However, previous settings either require time-consuming manual masks of target objects at the first frame during inference or lack the flexibility to specify arbitrary objects of interest. To address these limitations, we propose the setting named Click Video Object Segmentation (ClickVOS) which segments objects of interest across the whole video according to a single click per object in the first frame. And we provide the extended datasets DAVIS-P and YouTubeVOSP that with point annotations to support this task. ClickVOS is of significant practical applications and research implications due to its only 1-2 seconds interaction time for indicating an object, comparing annotating the mask of an object needs several minutes. However, ClickVOS also presents increased challenges. To address this task, we propose an end-to-end baseline approach named called Attention Before Segmentation (ABS), motivated by the attention process of humans. ABS utilizes the given point in the first frame to perceive the target object through a concise yet effective segmentation attention. Although the initial object mask is possibly inaccurate, in our ABS, as the video goes on, the initially imprecise object mask can self-heal instead of deteriorating due to error accumulation, which is attributed to our designed improvement memory that continuously records stable global object memory and updates detailed dense memory. In addition, we conduct various baseline explorations utilizing off-the-shelf algorithms from related fields, which could provide insights for the further exploration of ClickVOS. The experimental results demonstrate the superiority of the proposed ABS approach. Extended datasets and codes will be available at https://github.com/PinxueGuo/ClickVOS.
Pre-trained diffusion models utilized for image generation encapsulate a substantial reservoir of a priori knowledge pertaining to intricate textures. Harnessing the potential of leveraging this a priori knowledge in the context of image super-resolution presents a compelling avenue. Nonetheless, prevailing diffusion-based methodologies presently overlook the constraints imposed by degradation information on the diffusion process. Furthermore, these methods fail to consider the spatial variability inherent in the estimated blur kernel, stemming from factors such as motion jitter and out-of-focus elements in open-environment scenarios. This oversight results in a notable deviation of the image super-resolution effect from fundamental realities. To address these concerns, we introduce a framework known as Adaptive Multi-modal Fusion of \textbf{S}patially Variant Kernel Refinement with Diffusion Model for Blind Image \textbf{S}uper-\textbf{R}esolution (SSR). Within the SSR framework, we propose a Spatially Variant Kernel Refinement (SVKR) module. SVKR estimates a Depth-Informed Kernel, which takes the depth information into account and is spatially variant. Additionally, SVKR enhance the accuracy of depth information acquired from LR images, allowing for mutual enhancement between the depth map and blur kernel estimates. Finally, we introduce the Adaptive Multi-Modal Fusion (AMF) module to align the information from three modalities: low-resolution images, depth maps, and blur kernels. This alignment can constrain the diffusion model to generate more authentic SR results. Quantitative and qualitative experiments affirm the superiority of our approach, while ablation experiments corroborate the effectiveness of the modules we have proposed.
The performance of CLIP in dynamic facial expression recognition (DFER) task doesn't yield exceptional results as observed in other CLIP-based classification tasks. While CLIP's primary objective is to achieve alignment between images and text in the feature space, DFER poses challenges due to the abstract nature of text and the dynamic nature of video, making label representation limited and perfect alignment difficult. To address this issue, we have designed A$^{3}$lign-DFER, which introduces a new DFER labeling paradigm to comprehensively achieve alignment, thus enhancing CLIP's suitability for the DFER task. Specifically, our A$^{3}$lign-DFER method is designed with multiple modules that work together to obtain the most suitable expanded-dimensional embeddings for classification and to achieve alignment in three key aspects: affective, dynamic, and bidirectional. We replace the input label text with a learnable Multi-Dimensional Alignment Token (MAT), enabling alignment of text to facial expression video samples in both affective and dynamic dimensions. After CLIP feature extraction, we introduce the Joint Dynamic Alignment Synchronizer (JAS), further facilitating synchronization and alignment in the temporal dimension. Additionally, we implement a Bidirectional Alignment Training Paradigm (BAP) to ensure gradual and steady training of parameters for both modalities. Our insightful and concise A$^{3}$lign-DFER method achieves state-of-the-art results on multiple DFER datasets, including DFEW, FERV39k, and MAFW. Extensive ablation experiments and visualization studies demonstrate the effectiveness of A$^{3}$lign-DFER. The code will be available in the future.
Reference features from a template or historical frames are crucial for visual object tracking. Prior works utilize all features from a fixed template or memory for visual object tracking. However, due to the dynamic nature of videos, the required reference historical information for different search regions at different time steps is also inconsistent. Therefore, using all features in the template and memory can lead to redundancy and impair tracking performance. To alleviate this issue, we propose a novel tracking paradigm, consisting of a relevance attention mechanism and a global representation memory, which can adaptively assist the search region in selecting the most relevant historical information from reference features. Specifically, the proposed relevance attention mechanism in this work differs from previous approaches in that it can dynamically choose and build the optimal global representation memory for the current frame by accessing cross-frame information globally. Moreover, it can flexibly read the relevant historical information from the constructed memory to reduce redundancy and counteract the negative effects of harmful information. Extensive experiments validate the effectiveness of the proposed method, achieving competitive performance on five challenging datasets with 71 FPS.