Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection

As a manner to augment pre-trained large language models (LLM), knowledge injection is critical to develop vertical domain large models and has been widely studied. Although most current approaches, including parameter-efficient fine-tuning (PEFT) and block expansion methods, uniformly apply knowledge across all LLM layers, it raises the question: are all layers equally crucial for knowledge injection? We begin by evaluating the importance of each layer in finding the optimal layer range for knowledge injection. Intuitively, the more important layers should play a more critical role in knowledge injection and deserve a denser injection. We observe performance dips in question-answering benchmarks after the removal or expansion of the shallow layers, and the degradation shrinks as the layer gets deeper, indicating that the shallow layers hold the key to knowledge injection. This insight leads us to propose the S strategy, a post-pretraining strategy of selectively enhancing shallow layers while pruning the less effective deep ones. Based on this strategy, we introduce Llama Slayer-8B and Llama Slayer-8B-Instruct. We experimented on the corpus of code $\&$ math and demonstrated the effectiveness of our strategy. Further experiments across different LLM, Mistral-7B, and a legal corpus confirmed the general applicability of the approach, underscoring its wide-ranging efficacy. Our code is available at: \https://github.com/txchen-USTC/Llama-Slayer

Mixture-of-Noises Enhanced Forgery-Aware Predictor for Multi-Face Manipulation Detection and Localization

With the advancement of face manipulation technology, forgery images in multi-face scenarios are gradually becoming a more complex and realistic challenge. Despite this, detection and localization methods for such multi-face manipulations remain underdeveloped. Traditional manipulation localization methods either indirectly derive detection results from localization masks, resulting in limited detection performance, or employ a naive two-branch structure to simultaneously obtain detection and localization results, which cannot effectively benefit the localization capability due to limited interaction between two tasks. This paper proposes a new framework, namely MoNFAP, specifically tailored for multi-face manipulation detection and localization. The MoNFAP primarily introduces two novel modules: the Forgery-aware Unified Predictor (FUP) Module and the Mixture-of-Noises Module (MNM). The FUP integrates detection and localization tasks using a token learning strategy and multiple forgery-aware transformers, which facilitates the use of classification information to enhance localization capability. Besides, motivated by the crucial role of noise information in forgery detection, the MNM leverages multiple noise extractors based on the concept of the mixture of experts to enhance the general RGB features, further boosting the performance of our framework. Finally, we establish a comprehensive benchmark for multi-face detection and localization and the proposed \textit{MoNFAP} achieves significant performance. The codes will be made available.

MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection

Recently, infrared small target detection (ISTD) has made significant progress, thanks to the development of basic models. Specifically, the structures combining convolutional networks with transformers can successfully extract both local and global features. However, the disadvantage of the transformer is also inherited, i.e., the quadratic computational complexity to the length of the sequence. Inspired by the recent basic model with linear complexity for long-distance modeling, called Mamba, we explore the potential of this state space model for ISTD task in terms of effectiveness and efficiency in the paper. However, directly applying Mamba achieves poor performance since local features, which are critical to detecting small targets, cannot be fully exploited. Instead, we tailor a Mamba-in-Mamba (MiM-ISTD) structure for efficient ISTD. Specifically, we treat the local patches as "visual sentences" and use the Outer Mamba to explore the global information. We then decompose each visual sentence into sub-patches as "visual words" and use the Inner Mamba to further explore the local information among words in the visual sentence with negligible computational costs. By aggregating the word and sentence features, the MiM-ISTD can effectively explore both global and local information. Experiments on NUAA-SIRST and IRSTD-1k show the superior accuracy and efficiency of our method. Specifically, MiM-ISTD is $10 \times$ faster than the SOTA method and reduces GPU memory usage by 73.4$\%$ when testing on $2048 \times 2048$ image, overcoming the computation and memory constraints on high-resolution infrared images. Source code is available at https://github.com/txchen-USTC/MiM-ISTD.

Bootstrapping Audio-Visual Segmentation by Strengthening Audio Cues

How to effectively interact audio with vision has garnered considerable interest within the multi-modality research field. Recently, a novel audio-visual segmentation (AVS) task has been proposed, aiming to segment the sounding objects in video frames under the guidance of audio cues. However, most existing AVS methods are hindered by a modality imbalance where the visual features tend to dominate those of the audio modality, due to a unidirectional and insufficient integration of audio cues. This imbalance skews the feature representation towards the visual aspect, impeding the learning of joint audio-visual representations and potentially causing segmentation inaccuracies. To address this issue, we propose AVSAC. Our approach features a Bidirectional Audio-Visual Decoder (BAVD) with integrated bidirectional bridges, enhancing audio cues and fostering continuous interplay between audio and visual modalities. This bidirectional interaction narrows the modality imbalance, facilitating more effective learning of integrated audio-visual representations. Additionally, we present a strategy for audio-visual frame-wise synchrony as fine-grained guidance of BAVD. This strategy enhances the share of auditory components in visual features, contributing to a more balanced audio-visual representation learning. Extensive experiments show that our method attains new benchmarks in AVS performance.

Towards More Unified In-context Visual Understanding

The rapid advancement of large language models (LLMs) has accelerated the emergence of in-context learning (ICL) as a cutting-edge approach in the natural language processing domain. Recently, ICL has been employed in visual understanding tasks, such as semantic segmentation and image captioning, yielding promising results. However, existing visual ICL framework can not enable producing content across multiple modalities, which limits their potential usage scenarios. To address this issue, we present a new ICL framework for visual understanding with multi-modal output enabled. First, we quantize and embed both text and visual prompt into a unified representational space, structured as interleaved in-context sequences. Then a decoder-only sparse transformer architecture is employed to perform generative modeling on them, facilitating in-context learning. Thanks to this design, the model is capable of handling in-context vision understanding tasks with multimodal output in a unified pipeline. Experimental results demonstrate that our model achieves competitive performance compared with specialized models and previous ICL baselines. Overall, our research takes a further step toward unified multimodal in-context learning.

CloudBrain-MRS: An Intelligent Cloud Computing Platform for in vivo Magnetic Resonance Spectroscopy Preprocessing, Quantification, and Analysis

Magnetic resonance spectroscopy (MRS) is an important clinical imaging method for the diagnosis of diseases. Spectrum is used to observe the signal intensity of metabolites or further infer their concentrations. Although the magnetic resonance vendors commonly provide basic functions of spectra plots and metabolite quantification, the widespread clinical research of MRS is still limited due to the lack of easy-to-use processing software or platform. To address this issue, we have developed CloudBrain-MRS, a cloud-based online platform that provides powerful hardware and advanced algorithms. The platform can be accessed simply through a web browser, without requiring any program installation on the user side. CloudBrain-MRS also integrates the classic LCModel and advanced artificial intelligence algorithms and supports batch preprocessing, quantification, and analysis of MRS data. Additionally, the platform offers useful functions: 1) Automatically statistical analysis to find biomarkers from the health and patient groups; 2) Consistency verification between the classic and artificial intelligence quantification algorithms; 3) Colorful and three-dimensional visualization for the easy observation of individual metabolite spectrum. Last, both healthy and mild cognitive impairment patient data are used to demonstrate the usefulness of the platform. To the best of our knowledge, this is the first cloud computing platform for in vivo MRS with artificial intelligence processing. We sincerely hope that this platform will facilitate efficient clinical research for MRS. CloudBrain-MRS is open-accessed at https://csrc.xmu.edu.cn/CloudBrain.html.

MultiModal-GPT: A Vision and Language Model for Dialogue with Humans

We present a vision and language model named MultiModal-GPT to conduct multi-round dialogue with humans. MultiModal-GPT can follow various instructions from humans, such as generating a detailed caption, counting the number of interested objects, and answering general questions from users. MultiModal-GPT is parameter-efficiently fine-tuned from OpenFlamingo, with Low-rank Adapter (LoRA) added both in the cross-attention part and the self-attention part of the language model. We first construct instruction templates with vision and language data for multi-modality instruction tuning to make the model understand and follow human instructions. We find the quality of training data is vital for the dialogue performance, where few data containing short answers can lead the model to respond shortly to any instructions. To further enhance the ability to chat with humans of the MultiModal-GPT, we utilize language-only instruction-following data to train the MultiModal-GPT jointly. The joint training of language-only and visual-language instructions with the \emph{same} instruction template effectively improves dialogue performance. Various demos show the ability of continuous dialogue of MultiModal-GPT with humans. Code, dataset, and demo are at https://github.com/open-mmlab/Multimodal-GPT

Temporal RoI Align for Video Object Recognition

Video object detection is challenging in the presence of appearance deterioration in certain video frames. Therefore, it is a natural choice to aggregate temporal information from other frames of the same video into the current frame. However, RoI Align, as one of the most core procedures of video detectors, still remains extracting features from a single-frame feature map for proposals, making the extracted RoI features lack temporal information from videos. In this work, considering the features of the same object instance are highly similar among frames in a video, a novel Temporal RoI Align operator is proposed to extract features from other frames feature maps for current frame proposals by utilizing feature similarity. The proposed Temporal RoI Align operator can extract temporal information from the entire video for proposals. We integrate it into single-frame video detectors and other state-of-the-art video detectors, and conduct quantitative experiments to demonstrate that the proposed Temporal RoI Align operator can consistently and significantly boost the performance. Besides, the proposed Temporal RoI Align can also be applied into video instance segmentation. Codes are available at https://github.com/open-mmlab/mmtracking

Mining Contextual Information Beyond Image for Semantic Segmentation

This paper studies the context aggregation problem in semantic image segmentation. The existing researches focus on improving the pixel representations by aggregating the contextual information within individual images. Though impressive, these methods neglect the significance of the representations of the pixels of the corresponding class beyond the input image. To address this, this paper proposes to mine the contextual information beyond individual images to further augment the pixel representations. We first set up a feature memory module, which is updated dynamically during training, to store the dataset-level representations of various categories. Then, we learn class probability distribution of each pixel representation under the supervision of the ground-truth segmentation. At last, the representation of each pixel is augmented by aggregating the dataset-level representations based on the corresponding class probability distribution. Furthermore, by utilizing the stored dataset-level representations, we also propose a representation consistent learning strategy to make the classification head better address intra-class compactness and inter-class dispersion. The proposed method could be effortlessly incorporated into existing segmentation frameworks (e.g., FCN, PSPNet, OCRNet and DeepLabV3) and brings consistent performance improvements. Mining contextual information beyond image allows us to report state-of-the-art performance on various benchmarks: ADE20K, LIP, Cityscapes and COCO-Stuff.

Towards Generalizable and Robust Face Manipulation Detection via Bag-of-local-feature

Over the past several years, in order to solve the problem of malicious abuse of facial manipulation technology, face manipulation detection technology has obtained considerable attention and achieved remarkable progress. However, most existing methods have very impoverished generalization ability and robustness. In this paper, we propose a novel method for face manipulation detection, which can improve the generalization ability and robustness by bag-of-local-feature. Specifically, we extend Transformers using bag-of-feature approach to encode inter-patch relationships, allowing it to learn local forgery features without any explicit supervision. Extensive experiments demonstrate that our method can outperform competing state-of-the-art methods on FaceForensics++, Celeb-DF and DeeperForensics-1.0 datasets.