Yufan Liu

Yufan Liu, Jiajiong Cao, Bing Li et al.

Transformer attracts much attention because of its ability to learn global relations and superior performance. In order to achieve higher performance, it is natural to distill complementary knowledge from Transformer to convolutional neural network (CNN). However, most existing knowledge distillation methods only consider homologous-architecture distillation, such as distilling knowledge from CNN to CNN. They may not be suitable when applying to cross-architecture scenarios, such as from Transformer to CNN. To deal with this problem, a novel cross-architecture knowledge distillation method is proposed. Specifically, instead of directly mimicking output/intermediate features of the teacher, partially cross attention projector and group-wise linear projector are introduced to align the student features with the teacher's in two projected feature spaces. And a multi-view robust training scheme is further presented to improve the robustness and stability of the framework. Extensive experiments show that the proposed method outperforms 14 state-of-the-arts on both small-scale and large-scale datasets.

Chenghao Zhang, Guanting Dong, Yufan Liu et al.

Large Language Models (LLMs) have advanced autonomous agents from deep search, which retrieves concise factual answers, to deep research, which synthesizes scattered evidence into long-form reports. However, verifiable multimodal deep research remains challenging due to open-ended synthesis without deterministic ground truth and the need to interleave textual arguments with visual evidence. We propose \textsc{Ptah}, a multi-agent harness for interleaved report generation. \textsc{Ptah} orchestrates the lifecycle from user query to rendered web report through planning, research, and writing stages, where specialized agents construct visual-aware plans, collect claim-grounded evidence, maintain source-aligned images in a \textit{Visual Working Memory}, and compose reports through declarative multimodal tool use. A verifier agent serves as the harness's acceptance function, enforcing factual grounding, citation fidelity, and cross-modal consistency throughout the workflow. We further introduce \textsc{Ptah}Eval, an evaluation protocol that augments existing benchmarks with image-level and presentation-level assessments. Experiments on deep research benchmarks show that \textsc{Ptah} produces more reliable, visually informative, and usable human-facing multimodal reports than strong baselines.

Yufan Liu, Daoyuan Ren, Zhipeng Zhang et al.

Feature compression is increasingly important for improving the efficiency of downstream tasks, especially in applications involving large-scale or multi-modal data. While existing methods typically rely on dedicated models for achieving specific compression ratios, they are often limited in flexibility and generalization. In particular, retraining is necessary when adapting to a new compression ratio. To address this limitation, we propose a novel and flexible Arbitrary Ratio Feature Compression (ARFC) framework, which supports any compression ratio with a single model, eliminating the need for multiple specialized models. At its core, the Arbitrary Ratio Compressor (ARC) is an auto-regressive model that performs compression via next-token prediction. This allows the compression ratio to be controlled at inference simply by adjusting the number of generated tokens. To enhance the quality of the compressed features, two key modules are introduced. The Mixture of Solutions (MoS) module refines the compressed tokens by utilizing multiple compression results (solutions), reducing uncertainty and improving robustness. The Entity Relation Graph Constraint (ERGC) is integrated into the training process to preserve semantic and structural relationships during compression. Extensive experiments on cross-modal retrieval, image classification, and image retrieval tasks across multiple datasets demonstrate that our method consistently outperforms existing approaches at various compression ratios. Notably, in some cases, it even surpasses the performance of the original, uncompressed features. These results validate the effectiveness and versatility of ARFC for practical, resource-constrained scenarios.

Yufan Liu, Wanqian Zhang, Dayan Wu et al.

Model inversion (MI) attack reconstructs the private training data of a target model given its output, posing a significant threat to deep learning models and data privacy. On one hand, most of existing MI methods focus on searching for latent codes to represent the target identity, yet this iterative optimization-based scheme consumes a huge number of queries to the target model, making it unrealistic especially in black-box scenario. On the other hand, some training-based methods launch an attack through a single forward inference, whereas failing to directly learn high-level mappings from prediction vectors to images. Addressing these limitations, we propose a novel Prediction-to-Image (P2I) method for black-box MI attack. Specifically, we introduce the Prediction Alignment Encoder to map the target model's output prediction into the latent code of StyleGAN. In this way, prediction vector space can be well aligned with the more disentangled latent space, thus establishing a connection between prediction vectors and the semantic facial features. During the attack phase, we further design the Aligned Ensemble Attack scheme to integrate complementary facial attributes of target identity for better reconstruction. Experimental results show that our method outperforms other SOTAs, e.g.,compared with RLB-MI, our method improves attack accuracy by 8.5% and reduces query numbers by 99% on dataset CelebA.

Jinming Lou, Wenyang Luo, Yufan Liu et al.

Diffusion transformers have gained substantial interest in diffusion generative modeling due to their outstanding performance. However, their computational demands, particularly the quadratic complexity of attention mechanisms and multi-step inference processes, present substantial bottlenecks that limit their practical applications. To address these challenges, we propose TokenCache, a novel acceleration method that leverages the token-based multi-block architecture of transformers to reduce redundant computations. TokenCache tackles three critical questions: (1) Which tokens should be pruned and reused by the caching mechanism to eliminate redundancy? (2) Which blocks should be targeted for efficient caching? (3) At which time steps should caching be applied to balance speed and quality? In response to these challenges, TokenCache introduces a Cache Predictor that hierarchically addresses these issues by (1) Token pruning: assigning importance scores to each token to determine which tokens to prune and reuse; (2) Block selection: allocating pruning ratio to each block to adaptively select blocks for caching; (3) Temporal Scheduling: deciding at which time steps to apply caching strategies. Experimental results across various models demonstrate that TokenCache achieves an effective trade-off between generation quality and inference speed for diffusion transformers.

Xun Guo, Mingwu Zheng, Liang Hou et al.

Text-guided image-to-video (I2V) generation aims to generate a coherent video that preserves the identity of the input image and semantically aligns with the input prompt. Existing methods typically augment pretrained text-to-video (T2V) models by either concatenating the image with noised video frames channel-wise before being fed into the model or injecting the image embedding produced by pretrained image encoders in cross-attention modules. However, the former approach often necessitates altering the fundamental weights of pretrained T2V models, thus restricting the model's compatibility within the open-source communities and disrupting the model's prior knowledge. Meanwhile, the latter typically fails to preserve the identity of the input image. We present I2V-Adapter to overcome such limitations. I2V-Adapter adeptly propagates the unnoised input image to subsequent noised frames through a cross-frame attention mechanism, maintaining the identity of the input image without any changes to the pretrained T2V model. Notably, I2V-Adapter only introduces a few trainable parameters, significantly alleviating the training cost and also ensures compatibility with existing community-driven personalized models and control tools. Moreover, we propose a novel Frame Similarity Prior to balance the motion amplitude and the stability of generated videos through two adjustable control coefficients. Our experimental results demonstrate that I2V-Adapter is capable of producing high-quality videos. This performance, coupled with its agility and adaptability, represents a substantial advancement in the field of I2V, particularly for personalized and controllable applications.

Mohammed Muqeeth, Haokun Liu, Yufan Liu et al. · utoronto

Recently, there has been a widespread proliferation of "expert" language models that are specialized to a specific task or domain through parameter-efficient fine-tuning. How can we recycle large collections of expert language models to improve zero-shot generalization to unseen tasks? In this work, we propose Post-Hoc Adaptive Tokenwise Gating Over an Ocean of Specialized Experts (PHATGOOSE), which learns to route among specialized modules that were produced through parameter-efficient fine-tuning. Unlike past methods that learn to route among specialized models, PHATGOOSE explores the possibility that zero-shot generalization will be improved if different experts can be adaptively chosen for each token and at each layer in the model. Crucially, our method is post-hoc - it does not require simultaneous access to the datasets used to create the specialized models and only requires a modest amount of additional compute after each expert model is trained. In experiments covering a range of specialized model collections and zero-shot generalization benchmarks, we find that PHATGOOSE outperforms past methods for post-hoc routing and, in some cases, outperforms explicit multitask training (which requires simultaneous data access). To better understand the routing strategy learned by PHATGOOSE, we perform qualitative experiments to validate that PHATGOOSE's performance stems from its ability to make adaptive per-token and per-module expert choices. We release all of our code to support future work on improving zero-shot generalization by recycling specialized experts.

Manyi Li, Yufan Liu, Lai Jiang et al.

Although unlearning-based defenses claim to purge Not-Safe-For-Work (NSFW) concepts from diffusion models (DMs), we reveals that this "forgetting" is largely an illusion. Unlearning partially disrupts the mapping between linguistic symbols and the underlying knowledge, which remains intact as dormant memories. We find that the distributional discrepancy in the denoising process serves as a measurable indicator of how much of the mapping is retained, also reflecting the strength of unlearning. Inspired by this, we propose IVO (Initial Latent Variable Optimization), a concise and powerful attack framework that reactivates these dormant memories by reconstructing the broken mappings. Through Image Inversion}, Adversarial Optimization and Reused Attack, IVO optimizes initial latent variables to realign the noise distribution of unlearned models with their original unsafe states. Extensive experiments across 8 widely used unlearning techniques demonstrate that IVO achieves superior attack success rates and strong semantic consistency, exposing fundamental flaws in current defenses. The code is available at anonymous.4open.science/r/IVO/. Warning: This paper has unsafe images that may offend some readers.

Xin Li, Kun Yuan, Bingchen Li et al.

This paper presents a review for the NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement. The challenge comprises two tracks: (i) Efficient Video Quality Assessment (KVQ), and (ii) Diffusion-based Image Super-Resolution (KwaiSR). Track 1 aims to advance the development of lightweight and efficient video quality assessment (VQA) models, with an emphasis on eliminating reliance on model ensembles, redundant weights, and other computationally expensive components in the previous IQA/VQA competitions. Track 2 introduces a new short-form UGC dataset tailored for single image super-resolution, i.e., the KwaiSR dataset. It consists of 1,800 synthetically generated S-UGC image pairs and 1,900 real-world S-UGC images, which are split into training, validation, and test sets using a ratio of 8:1:1. The primary objective of the challenge is to drive research that benefits the user experience of short-form UGC platforms such as Kwai and TikTok. This challenge attracted 266 participants and received 18 valid final submissions with corresponding fact sheets, significantly contributing to the progress of short-form UGC VQA and image superresolution. The project is publicly available at https://github.com/lixinustc/KVQE- ChallengeCVPR-NTIRE2025.

Xiaoye Liang, Lai Jiang, Minglang Qiao et al.

In recent years, the development of burst imaging technology has improved the capture and processing capabilities of visual data, enabling a wide range of applications. However, the redundancy in burst images leads to the increased storage and transmission demands, as well as reduced efficiency of downstream tasks. To address this, we propose a new task of Burst Image Quality Assessment (BuIQA), to evaluate the task-driven quality of each frame within a burst sequence, providing reasonable cues for burst image selection. Specifically, we establish the first benchmark dataset for BuIQA, consisting of $7,346$ burst sequences with $45,827$ images and $191,572$ annotated quality scores for multiple downstream scenarios. Inspired by the data analysis, a unified BuIQA framework is proposed to achieve an efficient adaption for BuIQA under diverse downstream scenarios. Specifically, a task-driven prompt generation network is developed with heterogeneous knowledge distillation, to learn the priors of the downstream task. Then, the task-aware quality assessment network is introduced to assess the burst image quality based on the task prompt. Extensive experiments across 10 downstream scenarios demonstrate the impressive BuIQA performance of the proposed approach, outperforming the state-of-the-art. Furthermore, it can achieve $0.33$ dB PSNR improvement in the downstream tasks of denoising and super-resolution, by applying our approach to select the high-quality burst frames.

Manyi Li, Renshuai Tao, Yufan Liu et al.

With the rapid advancement of deep learning, particularly through generative adversarial networks (GANs) and diffusion models (DMs), AI-generated images, or ``deepfakes", have become nearly indistinguishable from real ones. These images are widely shared across Online Social Networks (OSNs), raising concerns about their misuse. Existing deepfake detection methods overlook the ``block effects" introduced by compression in OSNs, which obscure deepfake artifacts, and primarily focus on raw images, rarely encountered in real-world scenarios. To address these challenges, we propose PLADA (Pay Less Attention to Deceptive Artifacts), a novel framework designed to tackle the lack of paired data and the ineffective use of compressed images. PLADA consists of two core modules: Block Effect Eraser (B2E), which uses a dual-stage attention mechanism to handle block effects, and Open Data Aggregation (ODA), which processes both paired and unpaired data to improve detection. Extensive experiments across 26 datasets demonstrate that PLADA achieves a remarkable balance in deepfake detection, outperforming SoTA methods in detecting deepfakes on OSNs, even with limited paired data and compression. More importantly, this work introduces the ``block effect" as a critical factor in deepfake detection, providing a robust solution for open-world scenarios. Our code is available at https://github.com/ManyiLee/PLADA.

Yuhao Xu, Yantai Yang, Zhenyang Fan et al.

The advent of Vision-Language-Action (VLA) models represents a significant leap for embodied intelligence, yet their immense computational demands critically hinder deployment on resource-constrained robotic platforms. Intuitively, low-bit quantization is a prevalent and preferred technique for large-scale model compression. However, we find that a systematic analysis of VLA model's quantization is fundamentally lacking. We argue that naively applying uniform-bit quantization from Large Language Models (LLMs) to robotics is flawed, as these methods prioritize passive data fidelity while ignoring how minor action deviations compound into catastrophic task failures. To bridge this gap, we introduce QVLA, the first action-centric quantization framework specifically designed for embodied control. In a sharp departure from the rigid, uniform-bit quantization of LLM-based methods, QVLA introduces a highly granular, channel-wise bit allocation strategy. Its core mechanism is to directly measure the final action-space sensitivity when quantizing each individual channel to various bit-widths. This process yields a precise, per-channel importance metric that guides a global optimization, which elegantly unifies quantization and pruning (0-bit) into a single, cohesive framework. Extensive evaluations on different baselines demonstrate the superiority of our approach. In the LIBERO, the quantization version of OpenVLA-OFT with our method requires only 29.2% of the original model's VRAM while maintaining 98.9% of its original performance and achieving a 1.49x speedup. This translates to a 22.6% performance improvement over the LLM-derived method SmoothQuant. Our work establishes a new, principled foundation for compressing VLA models in robotics, paving the way for deploying powerful, large-scale models on real-world hardware. Code will be released.

Hanshi Wang, Yuhao Xu, Zekun Xu et al.

The established redundancy in visual tokens within large vision-language models allows pruning to effectively reduce their substantial computational demands. Previous methods typically employ heuristic layer-specific pruning strategies where, although the number of tokens removed may differ across decoder layers, the overall pruning schedule is fixed and applied uniformly to all input samples and tasks, failing to align token elimination with the model's holistic reasoning trajectory. Cognitive science indicates that human visual processing often begins with broad exploration to accumulate evidence before narrowing focus as the target becomes distinct. Our experiments reveal an analogous pattern in these models. This observation suggests that neither a fixed pruning schedule nor a heuristic layer-wise strategy can optimally accommodate the diverse complexities inherent in different inputs. To overcome this limitation, we introduce Complexity-Adaptive Pruning (AutoPrune), a training-free, plug-and-play framework that tailors pruning policies to varying sample and task complexities. Specifically, AutoPrune quantifies the mutual information between visual and textual tokens, then projects this signal to a budget-constrained logistic retention curve. Each such logistic curve, defined by its unique shape, corresponds to the specific complexity of different tasks and can guarantee adherence to predefined computational constraints. We evaluate AutoPrune on standard vision-language tasks and on Vision-Language-Action models for autonomous driving. Notably, when applied to LLaVA-1.5-7B, our method prunes 89% of visual tokens and reduces inference FLOPs by 76.8% while retaining 96.7% of the original accuracy averaged over all tasks. This corresponds to a 9.1% improvement over the recent work PDrop, demonstrating the effectiveness. Code is available at https://github.com/AutoLab-SAI-SJTU/AutoPrune.

Shengxi Li, Zifu Zhang, Mai Xu et al.

The emerging semantic compression has been receiving increasing research efforts most recently, capable of achieving high fidelity restoration during compression, even at extremely low bitrates. However, existing semantic compression methods typically combine standard pipelines with either pre-defined or high-dimensional semantics, thus suffering from deficiency in compression. To address this issue, we propose a novel hierarchical semantic compression (HSC) framework that purely operates within intrinsic semantic spaces from generative models, which is able to achieve efficient compression for consistent semantic restoration. More specifically, we first analyse the entropy models for the semantic compression, which motivates us to employ a hierarchical architecture based on a newly developed general inversion encoder. Then, we propose the feature compression network (FCN) and semantic compression network (SCN), such that the middle-level semantic feature and core semantics are hierarchically compressed to restore both accuracy and consistency of image semantics, via an entropy model progressively shared by channel-wise context. Experimental results demonstrate that the proposed HSC framework achieves the state-of-the-art performance on subjective quality and consistency for human vision, together with superior performances on machine vision tasks given compressed bitstreams. This essentially coincides with human visual system in understanding images, thus providing a new framework for future image/video compression paradigms. Our code shall be released upon acceptance.

Yufan Liu, Jinyang An, Wanqian Zhang et al.

The remarkable development of text-to-image generation models has raised notable security concerns, such as the infringement of portrait rights and the generation of inappropriate content. Concept erasure has been proposed to remove the model's knowledge about protected and inappropriate concepts. Although many methods have tried to balance the efficacy (erasing target concepts) and specificity (retaining irrelevant concepts), they can still generate abundant erasure concepts under the steering of semantically related inputs. In this work, we propose RealEra to address this "concept residue" issue. Specifically, we first introduce the mechanism of neighbor-concept mining, digging out the associated concepts by adding random perturbation into the embedding of erasure concept, thus expanding the erasing range and eliminating the generations even through associated concept inputs. Furthermore, to mitigate the negative impact on the generation of irrelevant concepts caused by the expansion of erasure scope, RealEra preserves the specificity through the beyond-concept regularization. This makes irrelevant concepts maintain their corresponding spatial position, thereby preserving their normal generation performance. We also employ the closed-form solution to optimize weights of U-Net for the cross-attention alignment, as well as the prediction noise alignment with the LoRA module. Extensive experiments on multiple benchmarks demonstrate that RealEra outperforms previous concept erasing methods in terms of superior erasing efficacy, specificity, and generality. More details are available on our project page https://realerasing.github.io/RealEra/ .

Tongfei Liu, Yufan Liu, Bing Li et al.

The high cost and accessibility problem associated with large datasets hinder the development of large-scale visual recognition systems. Dataset Distillation addresses these problems by synthesizing compact surrogate datasets for efficient training, storage, transfer, and privacy preservation. The existing state-of-the-art diffusion-based dataset distillation methods face three issues: lack of theoretical justification, poor efficiency in scaling to high data volumes, and failure in data-free scenarios. To address these issues, we establish a theoretical framework that justifies the use of diffusion models by proving the equivalence between dataset distillation and distribution matching, and reveals an inherent efficiency limit in the dataset distillation paradigm. We then propose a Dataset Concentration (DsCo) framework that uses a diffusion-based Noise-Optimization (NOpt) method to synthesize a small yet representative set of samples, and optionally augments the synthetic data via "Doping", which mixes selected samples from the original dataset with the synthetic samples to overcome the efficiency limit of dataset distillation. DsCo is applicable in both data-accessible and data-free scenarios, achieving SOTA performances for low data volumes, and it extends well to high data volumes, where it nearly reduces the dataset size by half with no performance degradation.

Wenyang Luo, Haina Qin, Zewen Chen et al.

Image restoration tasks like deblurring, denoising, and dehazing usually need distinct models for each degradation type, restricting their generalization in real-world scenarios with mixed or unknown degradations. In this work, we propose \textbf{Defusion}, a novel all-in-one image restoration framework that utilizes visual instruction-guided degradation diffusion. Unlike existing methods that rely on task-specific models or ambiguous text-based priors, Defusion constructs explicit \textbf{visual instructions} that align with the visual degradation patterns. These instructions are grounded by applying degradations to standardized visual elements, capturing intrinsic degradation features while agnostic to image semantics. Defusion then uses these visual instructions to guide a diffusion-based model that operates directly in the degradation space, where it reconstructs high-quality images by denoising the degradation effects with enhanced stability and generalizability. Comprehensive experiments demonstrate that Defusion outperforms state-of-the-art methods across diverse image restoration tasks, including complex and real-world degradations.

Yufan Liu, Wanqian Zhang, Huashan Chen et al.

Despite rapid advancements in text-to-image (T2I) models, their safety mechanisms are vulnerable to adversarial prompts, which maliciously generate unsafe images. Current red-teaming methods for proactively assessing such vulnerabilities usually require white-box access to T2I models, and rely on inefficient per-prompt optimization, as well as inevitably generate semantically meaningless prompts easily blocked by filters. In this paper, we propose APT (AutoPrompT), a black-box framework that leverages large language models (LLMs) to automatically generate human-readable adversarial suffixes for benign prompts. We first introduce an alternating optimization-finetuning pipeline between adversarial suffix optimization and fine-tuning the LLM utilizing the optimized suffix. Furthermore, we integrates a dual-evasion strategy in optimization phase, enabling the bypass of both perplexity-based filter and blacklist word filter: (1) we constrain the LLM generating human-readable prompts through an auxiliary LLM perplexity scoring, which starkly contrasts with prior token-level gibberish, and (2) we also introduce banned-token penalties to suppress the explicit generation of banned-tokens in blacklist. Extensive experiments demonstrate the excellent red-teaming performance of our human-readable, filter-resistant adversarial prompts, as well as superior zero-shot transferability which enables instant adaptation to unseen prompts and exposes critical vulnerabilities even in commercial APIs (e.g., Leonardo.Ai.).

Minglang Qiao, Yufan Liu, Mai Xu et al.

Visual and audio events simultaneously occur and both attract attention. However, most existing saliency prediction works ignore the influence of audio and only consider vision modality. In this paper, we propose a multitask learning method for visual-audio saliency prediction and sound source localization on multi-face video by leveraging visual, audio and face information. Specifically, we first introduce a large-scale database of multi-face video in visual-audio condition (MVVA), containing eye-tracking data and sound source annotations. Using this database, we find that sound influences human attention, and conversly attention offers a cue to determine sound source on multi-face video. Guided by these findings, a visual-audio multi-task network (VAM-Net) is introduced to predict saliency and locate sound source. VAM-Net consists of three branches corresponding to visual, audio and face modalities. Visual branch has a two-stream architecture to capture spatial and temporal information. Face and audio branches encode audio signals and faces, respectively. Finally, a spatio-temporal multi-modal graph (STMG) is constructed to model the interaction among multiple faces. With joint optimization of these branches, the intrinsic correlation of the tasks of saliency prediction and sound source localization is utilized and their performance is boosted by each other. Experiments show that the proposed method outperforms 12 state-of-the-art saliency prediction methods, and achieves competitive results in sound source localization.

Zekun Li, Yufan Liu, Bing Li et al.

Although transformer has achieved great progress on computer vision tasks, the scale variation in dense image prediction is still the key challenge. Few effective multi-scale techniques are applied in transformer and there are two main limitations in the current methods. On one hand, self-attention module in vanilla transformer fails to sufficiently exploit the diversity of semantic information because of its rigid mechanism. On the other hand, it is hard to build attention and interaction among different levels due to the heavy computational burden. To alleviate this problem, we first revisit multi-scale problem in dense prediction, verifying the significance of diverse semantic representation and multi-scale interaction, and exploring the adaptation of transformer to pyramidal structure. Inspired by these findings, we propose a novel Semantic-aware Decoupled Transformer Pyramid (SDTP) for dense image prediction, consisting of Intra-level Semantic Promotion (ISP), Cross-level Decoupled Interaction (CDI) and Attention Refinement Function (ARF). ISP explores the semantic diversity in different receptive space. CDI builds the global attention and interaction among different levels in decoupled space which also solves the problem of heavy computation. Besides, ARF is further added to refine the attention in transformer. Experimental results demonstrate the validity and generality of the proposed method, which outperforms the state-of-the-art by a significant margin in dense image prediction tasks. Furthermore, the proposed components are all plug-and-play, which can be embedded in other methods.

Yufan Liu, Minglang Qiao, Mai Xu et al.

Recently, video streams have occupied a large proportion of Internet traffic, most of which contain human faces. Hence, it is necessary to predict saliency on multiple-face videos, which can provide attention cues for many content based applications. However, most of multiple-face saliency prediction works only consider visual information and ignore audio, which is not consistent with the naturalistic scenarios. Several behavioral studies have established that sound influences human attention, especially during the speech turn-taking in multiple-face videos. In this paper, we thoroughly investigate such influences by establishing a large-scale eye-tracking database of Multiple-face Video in Visual-Audio condition (MVVA). Inspired by the findings of our investigation, we propose a novel multi-modal video saliency model consisting of three branches: visual, audio and face. The visual branch takes the RGB frames as the input and encodes them into visual feature maps. The audio and face branches encode the audio signal and multiple cropped faces, respectively. A fusion module is introduced to integrate the information from three modalities, and to generate the final saliency map. Experimental results show that the proposed method outperforms 11 state-of-the-art saliency prediction works. It performs closer to human multi-modal attention.

Zekun Li, Yufan Liu, Bing Li et al.

Although object detection has reached a milestone thanks to the great success of deep learning, the scale variation is still the key challenge. Integrating multi-level features is presented to alleviate the problems, like the classic Feature Pyramid Network (FPN) and its improvements. However, the specifically designed feature integration modules of these methods may not have the optimal architecture for feature fusion. Moreover, these models have fixed architectures and data flow paths, when fed with various samples. They cannot adjust and be compatible with each kind of data. To overcome the above limitations, we propose a Dynamic Sample-Individualized Connector (DSIC) for multi-scale object detection. It dynamically adjusts network connections to fit different samples. In particular, DSIC consists of two components: Intra-scale Selection Gate (ISG) and Cross-scale Selection Gate (CSG). ISG adaptively extracts multi-level features from backbone as the input of feature integration. CSG automatically activate informative data flow paths based on the multi-level features. Furthermore, these two components are both plug-and-play and can be embedded in any backbone. Experimental results demonstrate that the proposed method outperforms the state-of-the-arts.