SoccerNet 2023 Challenges Results

The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurring in the video broadcasts: (1) action spotting, focusing on retrieving all timestamps related to global actions in soccer, (2) ball action spotting, focusing on retrieving all timestamps related to the soccer ball change of state, and (3) dense video captioning, focusing on describing the broadcast with natural language and anchored timestamps. The second theme, field understanding, relates to the single task of (4) camera calibration, focusing on retrieving the intrinsic and extrinsic camera parameters from images. The third and last theme, player understanding, is composed of three low-level tasks related to extracting information about the players: (5) re-identification, focusing on retrieving the same players across multiple views, (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams, and (7) jersey number recognition, focusing on recognizing the jersey number of players from tracklets. Compared to the previous editions of the SoccerNet challenges, tasks (2-3-7) are novel, including new annotations and data, task (4) was enhanced with more data and annotations, and task (6) now focuses on end-to-end approaches. More information on the tasks, challenges, and leaderboards are available on https://www.soccer-net.org. Baselines and development kits can be found on https://github.com/SoccerNet.

SAM-PARSER: Fine-tuning SAM Efficiently by Parameter Space Reconstruction

Segment Anything Model (SAM) has received remarkable attention as it offers a powerful and versatile solution for object segmentation in images. However, fine-tuning SAM for downstream segmentation tasks under different scenarios remains a challenge, as the varied characteristics of different scenarios naturally requires diverse model parameter spaces. Most existing fine-tuning methods attempt to bridge the gaps among different scenarios by introducing a set of new parameters to modify SAM's original parameter space. Unlike these works, in this paper, we propose fine-tuning SAM efficiently by parameter space reconstruction (SAM-PARSER), which introduce nearly zero trainable parameters during fine-tuning. In SAM-PARSER, we assume that SAM's original parameter space is relatively complete, so that its bases are able to reconstruct the parameter space of a new scenario. We obtain the bases by matrix decomposition, and fine-tuning the coefficients to reconstruct the parameter space tailored to the new scenario by an optimal linear combination of the bases. Experimental results show that SAM-PARSER exhibits superior segmentation performance across various scenarios, while reducing the number of trainable parameters by $\approx 290$ times compared with current parameter-efficient fine-tuning methods.

Joint Gaze-Location and Gaze-Object Detection

This paper proposes an efficient and effective method for joint gaze location detection (GL-D) and gaze object detection (GO-D), \emph{i.e.}, gaze following detection. Current approaches frame GL-D and GO-D as two separate tasks, employing a multi-stage framework where human head crops must first be detected and then be fed into a subsequent GL-D sub-network, which is further followed by an additional object detector for GO-D. In contrast, we reframe the gaze following detection task as detecting human head locations and their gaze followings simultaneously, aiming at jointly detect human gaze location and gaze object in a unified and single-stage pipeline. To this end, we propose GTR, short for \underline{G}aze following detection \underline{TR}ansformer, streamlining the gaze following detection pipeline by eliminating all additional components, leading to the first unified paradigm that unites GL-D and GO-D in a fully end-to-end manner. GTR enables an iterative interaction between holistic semantics and human head features through a hierarchical structure, inferring the relations of salient objects and human gaze from the global image context and resulting in an impressive accuracy. Concretely, GTR achieves a 12.1 mAP gain ($\mathbf{25.1}\%$) on GazeFollowing and a 18.2 mAP gain ($\mathbf{43.3\%}$) on VideoAttentionTarget for GL-D, as well as a 19 mAP improvement ($\mathbf{45.2\%}$) on GOO-Real for GO-D. Meanwhile, unlike existing systems detecting gaze following sequentially due to the need for a human head as input, GTR has the flexibility to comprehend any number of people's gaze followings simultaneously, resulting in high efficiency. Specifically, GTR introduces over a $\times 9$ improvement in FPS and the relative gap becomes more pronounced as the human number grows.

Agglomerative Transformer for Human-Object Interaction Detection

We propose an agglomerative Transformer (AGER) that enables Transformer-based human-object interaction (HOI) detectors to flexibly exploit extra instance-level cues in a single-stage and end-to-end manner for the first time. AGER acquires instance tokens by dynamically clustering patch tokens and aligning cluster centers to instances with textual guidance, thus enjoying two benefits: 1) Integrality: each instance token is encouraged to contain all discriminative feature regions of an instance, which demonstrates a significant improvement in the extraction of different instance-level cues and subsequently leads to a new state-of-the-art performance of HOI detection with 36.75 mAP on HICO-Det. 2) Efficiency: the dynamical clustering mechanism allows AGER to generate instance tokens jointly with the feature learning of the Transformer encoder, eliminating the need of an additional object detector or instance decoder in prior methods, thus allowing the extraction of desirable extra cues for HOI detection in a single-stage and end-to-end pipeline. Concretely, AGER reduces GFLOPs by 8.5% and improves FPS by 36%, even compared to a vanilla DETR-like pipeline without extra cue extraction.

Secrets of RLHF in Large Language Models Part I: PPO

Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. Its primary objective is to function as a human-centric (helpful, honest, and harmless) assistant. Alignment with humans assumes paramount significance, and reinforcement learning with human feedback (RLHF) emerges as the pivotal technological paradigm underpinning this pursuit. Current technical routes usually include \textbf{reward models} to measure human preferences, \textbf{Proximal Policy Optimization} (PPO) to optimize policy model outputs, and \textbf{process supervision} to improve step-by-step reasoning capabilities. However, due to the challenges of reward design, environment interaction, and agent training, coupled with huge trial and error cost of large language models, there is a significant barrier for AI researchers to motivate the development of technical alignment and safe landing of LLMs. The stable training of RLHF has still been a puzzle. In the first report, we dissect the framework of RLHF, re-evaluate the inner workings of PPO, and explore how the parts comprising PPO algorithms impact policy agent training. We identify policy constraints being the key factor for the effective implementation of the PPO algorithm. Therefore, we explore the PPO-max, an advanced version of PPO algorithm, to efficiently improve the training stability of the policy model. Based on our main results, we perform a comprehensive analysis of RLHF abilities compared with SFT models and ChatGPT. The absence of open-source implementations has posed significant challenges to the investigation of LLMs alignment. Therefore, we are eager to release technical reports, reward models and PPO codes, aiming to make modest contributions to the advancement of LLMs.

Neural LerPlane Representations for Fast 4D Reconstruction of Deformable Tissues

Reconstructing deformable tissues from endoscopic stereo videos in robotic surgery is crucial for various clinical applications. However, existing methods relying only on implicit representations are computationally expensive and require dozens of hours, which limits further practical applications. To address this challenge, we introduce LerPlane, a novel method for fast and accurate reconstruction of surgical scenes under a single-viewpoint setting. LerPlane treats surgical procedures as 4D volumes and factorizes them into explicit 2D planes of static and dynamic fields, leading to a compact memory footprint and significantly accelerated optimization. The efficient factorization is accomplished by fusing features obtained through linear interpolation of each plane and enables using lightweight neural networks to model surgical scenes. Besides, LerPlane shares static fields, significantly reducing the workload of dynamic tissue modeling. We also propose a novel sample scheme to boost optimization and improve performance in regions with tool occlusion and large motions. Experiments on DaVinci robotic surgery videos demonstrate that LerPlane accelerates optimization by over 100$\times$ while maintaining high quality across various non-rigid deformations, showing significant promise for future intraoperative surgery applications.

Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation

In semi-supervised medical image segmentation, there exist empirical mismatch problems between labeled and unlabeled data distribution. The knowledge learned from the labeled data may be largely discarded if treating labeled and unlabeled data separately or in an inconsistent manner. We propose a straightforward method for alleviating the problem - copy-pasting labeled and unlabeled data bidirectionally, in a simple Mean Teacher architecture. The method encourages unlabeled data to learn comprehensive common semantics from the labeled data in both inward and outward directions. More importantly, the consistent learning procedure for labeled and unlabeled data can largely reduce the empirical distribution gap. In detail, we copy-paste a random crop from a labeled image (foreground) onto an unlabeled image (background) and an unlabeled image (foreground) onto a labeled image (background), respectively. The two mixed images are fed into a Student network and supervised by the mixed supervisory signals of pseudo-labels and ground-truth. We reveal that the simple mechanism of copy-pasting bidirectionally between labeled and unlabeled data is good enough and the experiments show solid gains (e.g., over 21% Dice improvement on ACDC dataset with 5% labeled data) compared with other state-of-the-arts on various semi-supervised medical image segmentation datasets. Code is available at https://github.com/DeepMed-Lab-ECNU/BCP}.

Segment Anything in 3D with NeRFs

The Segment Anything Model (SAM) has demonstrated its effectiveness in segmenting any object/part in various 2D images, yet its ability for 3D has not been fully explored. The real world is composed of numerous 3D scenes and objects. Due to the scarcity of accessible 3D data and high cost of its acquisition and annotation, lifting SAM to 3D is a challenging but valuable research avenue. With this in mind, we propose a novel framework to Segment Anything in 3D, named SA3D. Given a neural radiance field (NeRF) model, SA3D allows users to obtain the 3D segmentation result of any target object via only one-shot manual prompting in a single rendered view. With input prompts, SAM cuts out the target object from the according view. The obtained 2D segmentation mask is projected onto 3D mask grids via density-guided inverse rendering. 2D masks from other views are then rendered, which are mostly uncompleted but used as cross-view self-prompts to be fed into SAM again. Complete masks can be obtained and projected onto mask grids. This procedure is executed via an iterative manner while accurate 3D masks can be finally learned. SA3D can adapt to various radiance fields effectively without any additional redesigning. The entire segmentation process can be completed in approximately two minutes without any engineering optimization. Our experiments demonstrate the effectiveness of SA3D in different scenes, highlighting the potential of SAM in 3D scene perception. The project page is at https://jumpat.github.io/SA3D/.