Jian Dong

Chengpeng Chen, Zichao Guo, Haien Zeng et al.

Feature reuse has been a key technique in light-weight convolutional neural networks (CNNs) architecture design. Current methods usually utilize a concatenation operator to keep large channel numbers cheaply (thus large network capacity) by reusing feature maps from other layers. Although concatenation is parameters- and FLOPs-free, its computational cost on hardware devices is non-negligible. To address this, this paper provides a new perspective to realize feature reuse implicitly and more efficiently instead of concatenation. A novel hardware-efficient RepGhost module is proposed for implicit feature reuse via reparameterization, instead of using concatenation operator. Based on the RepGhost module, we develop our efficient RepGhost bottleneck and RepGhostNet. Experiments on ImageNet and COCO benchmarks demonstrate that our RepGhostNet is much more effective and efficient than GhostNet and MobileNetV3 on mobile devices. Specially, our RepGhostNet surpasses GhostNet 0.5x by 2.5% Top-1 accuracy on ImageNet dataset with less parameters and comparable latency on an ARM-based mobile device. Code and model weights are available at https://github.com/ChengpengChen/RepGhost.

Wei Zhang, Ping Zhang, Jian Dong et al.

The effectiveness of ad creatives is greatly influenced by their visual appearance. Advertising platforms can generate ad creatives with different appearances by combining creative elements provided by advertisers. However, with the increasing number of ad creative elements, it becomes challenging to select a suitable combination from the countless possibilities. The industry's mainstream approach is to select individual creative elements independently, which often overlooks the importance of interaction between creative elements during the modeling process. In response, this paper proposes a Cross-Element Combinatorial Selection framework for multiple creative elements, termed CECS. In the encoder process, a cross-element interaction is adopted to dynamically adjust the expression of a single creative element based on the current candidate creatives. In the decoder process, the creative combination problem is transformed into a cascade selection problem of multiple creative elements. A pointer mechanism with a cascade design is used to model the associations among candidates. Comprehensive experiments on real-world datasets show that CECS achieved the SOTA score on offline metrics. Moreover, the CECS algorithm has been deployed in our industrial application, resulting in a significant 6.02% CTR and 10.37% GMV lift, which is beneficial to the business.

Jian Dong, Yisong Yu, Yapeng Zhang et al.

User behaviors on an e-commerce app not only contain different kinds of feedback on items but also sometimes imply the cognitive clue of the user's decision-making. For understanding the psychological procedure behind user decisions, we present the behavior path and propose to match the user's current behavior path with historical behavior paths to predict user behaviors on the app. Further, we design a deep neural network for behavior path matching and solve three difficulties in modeling behavior paths: sparsity, noise interference, and accurate matching of behavior paths. In particular, we leverage contrastive learning to augment user behavior paths, provide behavior path self-activation to alleviate the effect of noise, and adopt a two-level matching mechanism to identify the most appropriate candidate. Our model shows excellent performance on two real-world datasets, outperforming the state-of-the-art CTR model. Moreover, our model has been deployed on the Meituan food delivery platform and has accumulated 1.6% improvement in CTR and 1.8% improvement in advertising revenue.

Ziliang Wang, Gaoyun Lin, Xuesi Wang et al.

Generative Recommendation (GR) reframes retrieval and ranking as autoregressive decoding over Semantic IDs (SIDs), unifying the multi-stage pipeline into a single model. Yet a fundamental expressive gap persists: discriminative models score items with direct feature access enabling explicit user-item crossing, whereas GR decodes over compact SID tokens without item-side signal. We formalize this via Bayes' theorem: ranking by p(y|f,u) is equivalent to ranking by p(f|y,u), which factorizes autoregressively over item features, showing that a generative model with full feature access matches its discriminative counterpart, with any practical gap stemming solely from incomplete feature coverage.We propose UniRec with Chain-of-Attribute (CoA) as its core mechanism. CoA prefixes each SID sequence with structured attribute tokens:category, seller, brand, before decoding the SID, recovering the item-side feature crossing that discriminative models exploit. Since items sharing identical attributes cluster in adjacent SID regions, attribute conditioning yields a measurable per-step entropy reduction H(s_k|s<k,a) < H(s_k|s<k), narrowing the search space and stabilizing beam search. We further address two deployment challenges: Capacity-constrained SID introduces exposure-weighted capacity penalties into residual quantization to suppress token collapse and the Matthew effect; Conditional Decoding Context (CDC) combines Task-Conditioned BOS with hash-based Content Summaries to inject scenario signals at each decoding step. A joint RFT and DPO framework aligns the model with business objectives beyond distribution matching.Experiments show UniRec outperforms the strongest baseline by +22.6% HR@50 overall and +15.5% on high-value orders. Deployed on Shopee's e-commerce platform, online A/B tests confirm significant gains in PVCTR (+5.37%), orders (+4.76%), and GMV (+5.60%).

Xiang Li, Shuwei Chen, Jian Dong et al.

Click-through rate (CTR) prediction is crucial in recommendation and online advertising systems. Existing methods usually model user behaviors, while ignoring the informative context which influences the user to make a click decision, e.g., click pages and pre-ranking candidates that inform inferences about user interests, leading to suboptimal performance. In this paper, we propose a Decision-Making Context Interaction Network (DCIN), which deploys a carefully designed Context Interaction Unit (CIU) to learn decision-making contexts and thus benefits CTR prediction. In addition, the relationship between different decision-making context sources is explored by the proposed Adaptive Interest Aggregation Unit (AIAU) to improve CTR prediction further. In the experiments on public and industrial datasets, DCIN significantly outperforms the state-of-the-art methods. Notably, the model has obtained the improvement of CTR+2.9%/CPM+2.1%/GMV+1.5% for online A/B testing and served the main traffic of Meituan Waimai advertising system.

Shuwei Chen, Xiang Li, Jian Dong et al.

Click-through rate (CTR) prediction plays a pivotal role in the success of recommendations. Inspired by the recent thriving of language models (LMs), a surge of works improve prediction by organizing user behavior data in a \textbf{textual} format and using LMs to understand user interest at a semantic level. While promising, these works have to truncate the textual data to reduce the quadratic computational overhead of self-attention in LMs. However, it has been studied that long user behavior data can significantly benefit CTR prediction. In addition, these works typically condense user diverse interests into a single feature vector, which hinders the expressive capability of the model. In this paper, we propose a \textbf{T}extual \textbf{B}ehavior-based \textbf{I}nterest Chunking \textbf{N}etwork (TBIN), which tackles the above limitations by combining an efficient locality-sensitive hashing algorithm and a shifted chunk-based self-attention. The resulting user diverse interests are dynamically activated, producing user interest representation towards the target item. Finally, the results of both offline and online experiments on real-world food recommendation platform demonstrate the effectiveness of TBIN.

Yimin Lv, Shuli Wang, Beihong Jin et al.

User behavior sequence modeling plays a significant role in Click-Through Rate (CTR) prediction on e-commerce platforms. Except for the interacted items, user behaviors contain rich interaction information, such as the behavior type, time, location, etc. However, so far, the information related to user behaviors has not yet been fully exploited. In the paper, we propose the concept of a situation and situational features for distinguishing interaction behaviors and then design a CTR model named Deep Situation-Aware Interaction Network (DSAIN). DSAIN first adopts the reparameterization trick to reduce noise in the original user behavior sequences. Then it learns the embeddings of situational features by feature embedding parameterization and tri-directional correlation fusion. Finally, it obtains the embedding of behavior sequence via heterogeneous situation aggregation. We conduct extensive offline experiments on three real-world datasets. Experimental results demonstrate the superiority of the proposed DSAIN model. More importantly, DSAIN has increased the CTR by 2.70\%, the CPM by 2.62\%, and the GMV by 2.16\% in the online A/B test. Now, DSAIN has been deployed on the Meituan food delivery platform and serves the main traffic of the Meituan takeout app.

Yin Cheng, Liao Zhou, Xiyu Liang et al.

Recommendation ranking is fundamentally an influence allocation problem: a sorting formula distributes ranking influence among competing factors, and the business outcome depends on finding the optimal "exchange rates" among them. However, offline proxy metrics systematically misjudge how influence reallocation translates to online impact, with asymmetric bias across metrics that a single calibration factor cannot correct. We present Sortify, the first fully autonomous LLM-driven ranking optimization agent deployed in a large-scale production recommendation system. The agent reframes ranking optimization as continuous influence exchange, closing the full loop from diagnosis to parameter deployment without human intervention. It addresses structural problems through three mechanisms: (1) a dual-channel framework grounded in Savage's Subjective Expected Utility (SEU) that decouples offline-online transfer correction (Belief channel) from constraint penalty adjustment (Preference channel); (2) an LLM meta-controller operating on framework-level parameters rather than low-level search variables; (3) a persistent Memory DB with 7 relational tables for cross-round learning. Its core metric, Influence Share, provides a decomposable measure where all factor contributions sum to exactly 100%. Sortify has been deployed across two markets. In Country A, the agent pushed GMV from -3.6% to +9.2% within 7 rounds with peak orders reaching +12.5%. In Country B, a cold-start deployment achieved +4.15% GMV/UU and +3.58% Ads Revenue in a 7-day A/B test, leading to full production rollout.

Peng Kuang, Xiangxiang Wang, Wentao Liu et al.

Multimodal Large Language Models (MLLMs) have achieved impressive performances in mathematical reasoning, yet they remain vulnerable to visual hallucinations and logical inconsistencies that standard outcome-based supervision fails to mitigate. While Process Reward Models (PRMs) promise step-by-step verification, current approaches typically operate as scalar scorers or generative critics that suffer from sycophancy, blindly validating the flawed hypotheses rather than grounding them in visual reality. To bridge this gap, we introduce TIM-PRM (Tool-Integrated Multimodal PRM), a novel agentic framework that transforms verification from a passive classification task into an active, tool-augmented investigation. TIM-PRM is trained to explicitly plan verification strategies and utilizes a mechanism of Independent Question Asking to query evidence via external tools, effectively decoupling verification from the reasoning context to eliminate confirmation bias. We instantiate this method by curating a high-quality dataset of tool-integrated verification trajectories. Extensive experiments on VisualProcessBench demonstrate that our 8B parameter model surpasses existing open-source multimodal PRMs, significantly outperforming much larger models like Qwen2.5-72B and InternVL-78B, while offering interpretable insights into the verification process.

Jun Guo, Wei Bao, Jiakai Wang et al.

Deep neural networks (DNNs) have achieved remarkable performance across a wide range of applications, while they are vulnerable to adversarial examples, which motivates the evaluation and benchmark of model robustness. However, current evaluations usually use simple metrics to study the performance of defenses, which are far from understanding the limitation and weaknesses of these defense methods. Thus, most proposed defenses are quickly shown to be attacked successfully, which results in the ``arm race'' phenomenon between attack and defense. To mitigate this problem, we establish a model robustness evaluation framework containing 23 comprehensive and rigorous metrics, which consider two key perspectives of adversarial learning (i.e., data and model). Through neuron coverage and data imperceptibility, we use data-oriented metrics to measure the integrity of test examples; by delving into model structure and behavior, we exploit model-oriented metrics to further evaluate robustness in the adversarial setting. To fully demonstrate the effectiveness of our framework, we conduct large-scale experiments on multiple datasets including CIFAR-10, SVHN, and ImageNet using different models and defenses with our open-source platform. Overall, our paper provides a comprehensive evaluation framework, where researchers could conduct comprehensive and fast evaluations using the open-source toolkit, and the analytical results could inspire deeper understanding and further improvement to the model robustness.

Zongxin Yang, Jian Dong, Ping Liu et al.

Comparing to image inpainting, image outpainting receives less attention due to two challenges in it. The first challenge is how to keep the spatial and content consistency between generated images and original input. The second challenge is how to maintain high quality in generated results, especially for multi-step generations in which generated regions are spatially far away from the initial input. To solve the two problems, we devise some innovative modules, named Skip Horizontal Connection and Recurrent Content Transfer, and integrate them into our designed encoder-decoder structure. By this design, our network can generate highly realistic outpainting prediction effectively and efficiently. Other than that, our method can generate new images with very long sizes while keeping the same style and semantic content as the given input. To test the effectiveness of the proposed architecture, we collect a new scenery dataset with diverse, complicated natural scenes. The experimental results on this dataset have demonstrated the efficacy of our proposed network. The code and dataset are available from https://github.com/z-x-yang/NS-Outpainting.

Hongsong Wang, Jian Dong, Bin Cheng et al.

Human motion prediction, which aims to predict future human poses given past poses, has recently seen increased interest. Many recent approaches are based on Recurrent Neural Networks (RNN) which model human poses with exponential maps. These approaches neglect the pose velocity as well as temporal relation of different poses, and tend to converge to the mean pose or fail to generate natural-looking poses. We therefore propose a novel Position-Velocity Recurrent Encoder-Decoder (PVRED) for human motion prediction, which makes full use of pose velocities and temporal positional information. A temporal position embedding method is presented and a Position-Velocity RNN (PVRNN) is proposed. We also emphasize the benefits of quaternion parameterization of poses and design a novel trainable Quaternion Transformation (QT) layer, which is combined with a robust loss function during training. We provide quantitative results for both short-term prediction in the future 0.5 seconds and long-term prediction in the future 0.5 to 1 seconds. Experiments on several benchmarks show that our approach considerably outperforms the state-of-the-art methods. In addition, qualitative visualizations in the future 4 seconds show that our approach could predict future human-like and meaningful poses in very long time horizons. Code is publicly available on GitHub: \textcolor{red}{https://github.com/hongsong-wang/PVRNN}.

Yaowen Bi, Yuteng Lian, Jie Cui et al.

Neural-based multi-task learning (MTL) has been successfully applied to many recommendation applications. However, these MTL models (e.g., MMoE, PLE) did not consider feature interaction during the optimization, which is crucial for capturing complex high-order features and has been widely used in ranking models for real-world recommender systems. Moreover, through feature importance analysis across various tasks in MTL, we have observed an interesting divergence phenomenon that the same feature can have significantly different importance across different tasks in MTL. To address these issues, we propose Deep Multiple Task-specific Feature Interactions Network (DTN) with a novel model structure design. DTN introduces multiple diversified task-specific feature interaction methods and task-sensitive network in MTL networks, enabling the model to learn task-specific diversified feature interaction representations, which improves the efficiency of joint representation learning in a general setup. We applied DTN to our company's real-world E-commerce recommendation dataset, which consisted of over 6.3 billion samples, the results demonstrated that DTN significantly outperformed state-of-the-art MTL models. Moreover, during online evaluation of DTN in a large-scale E-commerce recommender system, we observed a 3.28% in clicks, a 3.10% increase in orders and a 2.70% increase in GMV (Gross Merchandise Value) compared to the state-of-the-art MTL models. Finally, extensive offline experiments conducted on public benchmark datasets demonstrate that DTN can be applied to various scenarios beyond recommendations, enhancing the performance of ranking models.

Hongli Zhou, Hui Huang, Ziqing Zhao et al.

The evaluation of large language models (LLMs) via benchmarks is widespread, yet inconsistencies between different leaderboards and poor separability among top models raise concerns about their ability to accurately reflect authentic model capabilities. This paper provides a critical analysis of benchmark effectiveness, examining mainstream prominent LLM benchmarks using results from diverse models. We first propose Pseudo-Siamese Network for Item Response Theory (PSN-IRT), an enhanced Item Response Theory framework that incorporates a rich set of item parameters within an IRT-grounded architecture. PSN-IRT can be utilized for accurate and reliable estimations of item characteristics and model abilities. Based on PSN-IRT, we conduct extensive analysis on 11 LLM benchmarks comprising 41,871 items, revealing significant and varied shortcomings in their measurement quality. Furthermore, we demonstrate that leveraging PSN-IRT is able to construct smaller benchmarks while maintaining stronger alignment with human preference.

Congxia Zhao, Xiongjun Fu, Jian Dong et al.

Synthetic aperture radar (SAR) imaging, celebrated for its high resolution, all-weather capability, and day-night operability, is indispensable for maritime applications. However, ship detection in SAR imagery faces significant challenges, including complex backgrounds, densely arranged targets, and large scale variations. To address these issues, we propose a novel framework, Center-Aware SAR Ship Detector (CASS-Det), designed for robust multi-scale and densely packed ship detection. CASS-Det integrates three key innovations: (1) a center enhancement module (CEM) that employs rotational convolution to emphasize ship centers, improving localization while suppressing background interference; (2) a neighbor attention module (NAM) that leverages cross-layer dependencies to refine ship boundaries in densely populated scenes; and (3) a cross-connected feature pyramid network (CC-FPN) that enhances multi-scale feature fusion by integrating shallow and deep features. Extensive experiments on the SSDD, HRSID, and LS-SSDD-v1.0 datasets demonstrate the state-of-the-art performance of CASS-Det, excelling at detecting multi-scale and densely arranged ships.

Yang Ye, Jingyuan Tan, Tianyue Jiang et al.

Training effective software engineering agents requires large volumes of task-specific trajectories, incurring substantial data construction costs. Inspired by the "Less-Is-More" hypothesis in mathematical reasoning, we investigate its extension to agentic scenarios and propose an end-to-end training framework that achieves superior agentic capabilities with fewer but higher-quality training trajectories. This is achieved via STITCH (Sliding-memory Trajectory Inference and Task Chunking Heuristic), a coarse-to-fine mechanism that filters low-value noise and retains decision-critical tokens to maximize training signal quality. We conduct experiments across multiple agent frameworks (e.g., mini-SWE-agent, MSWE-agent), model scales (30B to 355B), and multilingual settings (Python, Java, and ArkTS). On SWE-bench Verified, models trained with STITCH achieve up to 63.16% relative improvement over base models. On Multi-SWE-bench (Java), MiniMax-M2.5-STITCH achieves 43.75% with our CodeArts Agent scaffold (+16.67%). On HarmonyOS (ArkTS), GLM-4.7-STITCH improves the compilation pass rate to 61.31% (+43.34%) with less than 1K training trajectories. Our results confirm that the "Less-Is-More" paradigm generalizes effectively to complex agentic tasks across diverse languages and model scales.

Xiaoguang Tu, Yingtian Zou, Jian Zhao et al.

We present a versatile model, FaceAnime, for various video generation tasks from still images. Video generation from a single face image is an interesting problem and usually tackled by utilizing Generative Adversarial Networks (GANs) to integrate information from the input face image and a sequence of sparse facial landmarks. However, the generated face images usually suffer from quality loss, image distortion, identity change, and expression mismatching due to the weak representation capacity of the facial landmarks. In this paper, we propose to "imagine" a face video from a single face image according to the reconstructed 3D face dynamics, aiming to generate a realistic and identity-preserving face video, with precisely predicted pose and facial expression. The 3D dynamics reveal changes of the facial expression and motion, and can serve as a strong prior knowledge for guiding highly realistic face video generation. In particular, we explore face video prediction and exploit a well-designed 3D dynamic prediction network to predict a 3D dynamic sequence for a single face image. The 3D dynamics are then further rendered by the sparse texture mapping algorithm to recover structural details and sparse textures for generating face frames. Our model is versatile for various AR/VR and entertainment applications, such as face video retargeting and face video prediction. Superior experimental results have well demonstrated its effectiveness in generating high-fidelity, identity-preserving, and visually pleasant face video clips from a single source face image.

Ping Lang, Xiongjun Fu, Marco Martorella et al.

Modern radar systems have high requirements in terms of accuracy, robustness and real-time capability when operating on increasingly complex electromagnetic environments. Traditional radar signal processing (RSP) methods have shown some limitations when meeting such requirements, particularly in matters of target classification. With the rapid development of machine learning (ML), especially deep learning, radar researchers have started integrating these new methods when solving RSP-related problems. This paper aims at helping researchers and practitioners to better understand the application of ML techniques to RSP-related problems by providing a comprehensive, structured and reasoned literature overview of ML-based RSP techniques. This work is amply introduced by providing general elements of ML-based RSP and by stating the motivations behind them. The main applications of ML-based RSP are then analysed and structured based on the application field. This paper then concludes with a series of open questions and proposed research directions, in order to indicate current gaps and potential future solutions and trends.

Xiaojie Jin, Xin Li, Huaxin Xiao et al.

In this work, we address the challenging video scene parsing problem by developing effective representation learning methods given limited parsing annotations. In particular, we contribute two novel methods that constitute a unified parsing framework. (1) \textbf{Predictive feature learning}} from nearly unlimited unlabeled video data. Different from existing methods learning features from single frame parsing, we learn spatiotemporal discriminative features by enforcing a parsing network to predict future frames and their parsing maps (if available) given only historical frames. In this way, the network can effectively learn to capture video dynamics and temporal context, which are critical clues for video scene parsing, without requiring extra manual annotations. (2) \textbf{Prediction steering parsing}} architecture that effectively adapts the learned spatiotemporal features to scene parsing tasks and provides strong guidance for any off-the-shelf parsing model to achieve better video scene parsing performance. Extensive experiments over two challenging datasets, Cityscapes and Camvid, have demonstrated the effectiveness of our methods by showing significant improvement over well-established baselines.

Xiaojie Jin, Yunpeng Chen, Jian Dong et al.

Intermediate features at different layers of a deep neural network are known to be discriminative for visual patterns of different complexities. However, most existing works ignore such cross-layer heterogeneities when classifying samples of different complexities. For example, if a training sample has already been correctly classified at a specific layer with high confidence, we argue that it is unnecessary to enforce rest layers to classify this sample correctly and a better strategy is to encourage those layers to focus on other samples. In this paper, we propose a layer-wise discriminative learning method to enhance the discriminative capability of a deep network by allowing its layers to work collaboratively for classification. Towards this target, we introduce multiple classifiers on top of multiple layers. Each classifier not only tries to correctly classify the features from its input layer, but also coordinates with other classifiers to jointly maximize the final classification performance. Guided by the other companion classifiers, each classifier learns to concentrate on certain training examples and boosts the overall performance. Allowing for end-to-end training, our method can be conveniently embedded into state-of-the-art deep networks. Experiments with multiple popular deep networks, including Network in Network, GoogLeNet and VGGNet, on scale-various object classification benchmarks, including CIFAR100, MNIST and ImageNet, and scene classification benchmarks, including MIT67, SUN397 and Places205, demonstrate the effectiveness of our method. In addition, we also analyze the relationship between the proposed method and classical conditional random fields models.

Jianan Li, Yunchao Wei, Xiaodan Liang et al.

Modern deep neural network based object detection methods typically classify candidate proposals using their interior features. However, global and local surrounding contexts that are believed to be valuable for object detection are not fully exploited by existing methods yet. In this work, we take a step towards understanding what is a robust practice to extract and utilize contextual information to facilitate object detection in practice. Specifically, we consider the following two questions: "how to identify useful global contextual information for detecting a certain object?" and "how to exploit local context surrounding a proposal for better inferring its contents?". We provide preliminary answers to these questions through developing a novel Attention to Context Convolution Neural Network (AC-CNN) based object detection model. AC-CNN effectively incorporates global and local contextual information into the region-based CNN (e.g. Fast RCNN) detection model and provides better object detection performance. It consists of one attention-based global contextualized (AGC) sub-network and one multi-scale local contextualized (MLC) sub-network. To capture global context, the AGC sub-network recurrently generates an attention map for an input image to highlight useful global contextual locations, through multiple stacked Long Short-Term Memory (LSTM) layers. For capturing surrounding local context, the MLC sub-network exploits both the inside and outside contextual information of each specific proposal at multiple scales. The global and local context are then fused together for making the final decision for detection. Extensive experiments on PASCAL VOC 2007 and VOC 2012 well demonstrate the superiority of the proposed AC-CNN over well-established baselines. In particular, AC-CNN outperforms the popular Fast-RCNN by 2.0% and 2.2% on VOC 2007 and VOC 2012 in terms of mAP, respectively.

Xiaodan Liang, Si Liu, Xiaohui Shen et al.

In this work, the human parsing task, namely decomposing a human image into semantic fashion/body regions, is formulated as an Active Template Regression (ATR) problem, where the normalized mask of each fashion/body item is expressed as the linear combination of the learned mask templates, and then morphed to a more precise mask with the active shape parameters, including position, scale and visibility of each semantic region. The mask template coefficients and the active shape parameters together can generate the human parsing results, and are thus called the structure outputs for human parsing. The deep Convolutional Neural Network (CNN) is utilized to build the end-to-end relation between the input human image and the structure outputs for human parsing. More specifically, the structure outputs are predicted by two separate networks. The first CNN network is with max-pooling, and designed to predict the template coefficients for each label mask, while the second CNN network is without max-pooling to preserve sensitivity to label mask position and accurately predict the active shape parameters. For a new image, the structure outputs of the two networks are fused to generate the probability of each label for each pixel, and super-pixel smoothing is finally used to refine the human parsing result. Comprehensive evaluations on a large dataset well demonstrate the significant superiority of the ATR framework over other state-of-the-arts for human parsing. In particular, the F1-score reaches $64.38\%$ by our ATR framework, significantly higher than $44.76\%$ based on the state-of-the-art algorithm.

Yunchao Wei, Wei Xia, Junshi Huang et al.

Convolutional Neural Network (CNN) has demonstrated promising performance in single-label image classification tasks. However, how CNN best copes with multi-label images still remains an open problem, mainly due to the complex underlying object layouts and insufficient multi-label training images. In this work, we propose a flexible deep CNN infrastructure, called Hypotheses-CNN-Pooling (HCP), where an arbitrary number of object segment hypotheses are taken as the inputs, then a shared CNN is connected with each hypothesis, and finally the CNN output results from different hypotheses are aggregated with max pooling to produce the ultimate multi-label predictions. Some unique characteristics of this flexible deep CNN infrastructure include: 1) no ground truth bounding box information is required for training; 2) the whole HCP infrastructure is robust to possibly noisy and/or redundant hypotheses; 3) no explicit hypothesis label is required; 4) the shared CNN may be well pre-trained with a large-scale single-label image dataset, e.g. ImageNet; and 5) it may naturally output multi-label prediction results. Experimental results on Pascal VOC2007 and VOC2012 multi-label image datasets well demonstrate the superiority of the proposed HCP infrastructure over other state-of-the-arts. In particular, the mAP reaches 84.2% by HCP only and 90.3% after the fusion with our complementary result in [47] based on hand-crafted features on the VOC2012 dataset, which significantly outperforms the state-of-the-arts with a large margin of more than 7%.