ReLU-KAN: New Kolmogorov-Arnold Networks that Only Need Matrix Addition, Dot Multiplication, and ReLU

Limited by the complexity of basis function (B-spline) calculations, Kolmogorov-Arnold Networks (KAN) suffer from restricted parallel computing capability on GPUs. This paper proposes a novel ReLU-KAN implementation that inherits the core idea of KAN. By adopting ReLU (Rectified Linear Unit) and point-wise multiplication, we simplify the design of KAN's basis function and optimize the computation process for efficient CUDA computing. The proposed ReLU-KAN architecture can be readily implemented on existing deep learning frameworks (e.g., PyTorch) for both inference and training. Experimental results demonstrate that ReLU-KAN achieves a 20x speedup compared to traditional KAN with 4-layer networks. Furthermore, ReLU-KAN exhibits a more stable training process with superior fitting ability while preserving the "catastrophic forgetting avoidance" property of KAN. You can get the code in https://github.com/quiqi/relu_kan

HARMamba: Efficient Wearable Sensor Human Activity Recognition Based on Bidirectional Selective SSM

Wearable sensor human activity recognition (HAR) is a crucial area of research in activity sensing. While transformer-based temporal deep learning models have been extensively studied and implemented, their large number of parameters present significant challenges in terms of system computing load and memory usage, rendering them unsuitable for real-time mobile activity recognition applications. Recently, an efficient hardware-aware state space model (SSM) called Mamba has emerged as a promising alternative. Mamba demonstrates strong potential in long sequence modeling, boasts a simpler network architecture, and offers an efficient hardware-aware design. Leveraging SSM for activity recognition represents an appealing avenue for exploration. In this study, we introduce HARMamba, which employs a more lightweight selective SSM as the foundational model architecture for activity recognition. The goal is to address the computational resource constraints encountered in real-time activity recognition scenarios. Our approach involves processing sensor data flow by independently learning each channel and segmenting the data into "patches". The marked sensor sequence's position embedding serves as the input token for the bidirectional state space model, ultimately leading to activity categorization through the classification head. Compared to established activity recognition frameworks like Transformer-based models, HARMamba achieves superior performance while also reducing computational and memory overhead. Furthermore, our proposed method has been extensively tested on four public activity datasets: PAMAP2, WISDM, UNIMIB, and UCI, demonstrating impressive performance in activity recognition tasks.

P2LHAP:Wearable sensor-based human activity recognition, segmentation and forecast through Patch-to-Label Seq2Seq Transformer

Traditional deep learning methods struggle to simultaneously segment, recognize, and forecast human activities from sensor data. This limits their usefulness in many fields such as healthcare and assisted living, where real-time understanding of ongoing and upcoming activities is crucial. This paper introduces P2LHAP, a novel Patch-to-Label Seq2Seq framework that tackles all three tasks in a efficient single-task model. P2LHAP divides sensor data streams into a sequence of "patches", served as input tokens, and outputs a sequence of patch-level activity labels including the predicted future activities. A unique smoothing technique based on surrounding patch labels, is proposed to identify activity boundaries accurately. Additionally, P2LHAP learns patch-level representation by sensor signal channel-independent Transformer encoders and decoders. All channels share embedding and Transformer weights across all sequences. Evaluated on three public datasets, P2LHAP significantly outperforms the state-of-the-art in all three tasks, demonstrating its effectiveness and potential for real-world applications.

Gemini: A Family of Highly Capable Multimodal Models

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of Gemini models in cross-modal reasoning and language understanding will enable a wide variety of use cases and we discuss our approach toward deploying them responsibly to users.

IG Captioner: Information Gain Captioners are Strong Zero-shot Classifiers

Generative training has been demonstrated to be powerful for building visual-language models. However, on zero-shot discriminative benchmarks, there is still a performance gap between models trained with generative and discriminative objectives. In this paper, we aim to narrow this gap by improving the efficacy of generative training on classification tasks, without any finetuning processes or additional modules. Specifically, we focus on narrowing the gap between the generative captioner and the CLIP classifier. We begin by analysing the predictions made by the captioner and classifier and observe that the caption generation inherits the distribution bias from the language model trained with pure text modality, making it less grounded on the visual signal. To tackle this problem, we redesign the scoring objective for the captioner to alleviate the distributional bias and focus on measuring the gain of information brought by the visual inputs. We further design a generative training objective to match the evaluation objective. We name our model trained and evaluated from the novel procedures as Information Gain (IG) captioner. We pretrain the models on the public Laion-5B dataset and perform a series of discriminative evaluations. For the zero-shot classification on ImageNet, IG captioner achieves $> 18\%$ improvements over the standard captioner, achieving comparable performances with the CLIP classifier. IG captioner also demonstrated strong performance on zero-shot image-text retrieval tasks on MSCOCO and Flickr30K. We hope this paper inspires further research towards unifying generative and discriminative training procedures for visual-language models.

A Multi-Task Deep Learning Approach for Sensor-based Human Activity Recognition and Segmentation

Sensor-based human activity segmentation and recognition are two important and challenging problems in many real-world applications and they have drawn increasing attention from the deep learning community in recent years. Most of the existing deep learning works were designed based on pre-segmented sensor streams and they have treated activity segmentation and recognition as two separate tasks. In practice, performing data stream segmentation is very challenging. We believe that both activity segmentation and recognition may convey unique information which can complement each other to improve the performance of the two tasks. In this paper, we firstly proposes a new multitask deep neural network to solve the two tasks simultaneously. The proposed neural network adopts selective convolution and features multiscale windows to segment activities of long or short time durations. First, multiple windows of different scales are generated to center on each unit of the feature sequence. Then, the model is trained to predict, for each window, the activity class and the offset to the true activity boundaries. Finally, overlapping windows are filtered out by non-maximum suppression, and adjacent windows of the same activity are concatenated to complete the segmentation task. Extensive experiments were conducted on eight popular benchmarking datasets, and the results show that our proposed method outperforms the state-of-the-art methods both for activity recognition and segmentation.

TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities

Recently, the success of pre-training in text domain has been fully extended to vision, audio, and cross-modal scenarios. The proposed pre-training models of different modalities are showing a rising trend of homogeneity in their model structures, which brings the opportunity to implement different pre-training models within a uniform framework. In this paper, we present TencentPretrain, a toolkit supporting pre-training models of different modalities. The core feature of TencentPretrain is the modular design. The toolkit uniformly divides pre-training models into 5 components: embedding, encoder, target embedding, decoder, and target. As almost all of common modules are provided in each component, users can choose the desired modules from different components to build a complete pre-training model. The modular design enables users to efficiently reproduce existing pre-training models or build brand-new one. We test the toolkit on text, vision, and audio benchmarks and show that it can match the performance of the original implementations.

Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners

This work explores an efficient approach to establish a foundational video-text model for tasks including open-vocabulary video classification, text-to-video retrieval, video captioning and video question-answering. We present VideoCoCa that reuses a pretrained image-text contrastive captioner (CoCa) model and adapt it to video-text tasks with minimal extra training. While previous works adapt image-text models with various cross-frame fusion modules (for example, cross-frame attention layer or perceiver resampler) and finetune the modified architecture on video-text data, we surprisingly find that the generative attentional pooling and contrastive attentional pooling layers in the image-text CoCa design are instantly adaptable to ``flattened frame embeddings'', yielding a strong zero-shot transfer baseline for many video-text tasks. Specifically, the frozen image encoder of a pretrained image-text CoCa takes each video frame as inputs and generates \(N\) token embeddings per frame for totally \(T\) video frames. We flatten \(N \times T\) token embeddings as a long sequence of frozen video representation and apply CoCa's generative attentional pooling and contrastive attentional pooling on top. All model weights including pooling layers are directly loaded from an image-text CoCa pretrained model. Without any video or video-text data, VideoCoCa's zero-shot transfer baseline already achieves state-of-the-art results on zero-shot video classification on Kinetics 400/600/700, UCF101, HMDB51, and Charades, as well as zero-shot text-to-video retrieval on MSR-VTT and ActivityNet Captions. We also explore lightweight finetuning on top of VideoCoCa, and achieve strong results on video question-answering (iVQA, MSRVTT-QA, MSVD-QA) and video captioning (MSR-VTT, ActivityNet, Youcook2). Our approach establishes a simple and effective video-text baseline for future research.

A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning

Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries, which are expensive and impractical for low-resource languages. To disengage from these dependencies, researchers have explored training multilingual models on English-only resources and transferring them to low-resource languages. However, its effect is limited by the gap between embedding clusters of different languages. To address this issue, we propose Embedding-Push, Attention-Pull, and Robust targets to transfer English embeddings to virtual multilingual embeddings without semantic loss, thereby improving cross-lingual transferability. Experimental results on mBERT and XLM-R demonstrate that our method significantly outperforms previous works on the zero-shot cross-lingual text classification task and can obtain a better multilingual alignment.

Multi-scale Attentive Image De-raining Networks via Neural Architecture Search

Multi-scale architectures and attention modules have shown effectiveness in many deep learning-based image de-raining methods. However, manually designing and integrating these two components into a neural network requires a bulk of labor and extensive expertise. In this article, a high-performance multi-scale attentive neural architecture search (MANAS) framework is technically developed for image deraining. The proposed method formulates a new multi-scale attention search space with multiple flexible modules that are favorite to the image de-raining task. Under the search space, multi-scale attentive cells are built, which are further used to construct a powerful image de-raining network. The internal multiscale attentive architecture of the de-raining network is searched automatically through a gradient-based search algorithm, which avoids the daunting procedure of the manual design to some extent. Moreover, in order to obtain a robust image de-raining model, a practical and effective multi-to-one training strategy is also presented to allow the de-raining network to get sufficient background information from multiple rainy images with the same background scene, and meanwhile, multiple loss functions including external loss, internal loss, architecture regularization loss, and model complexity loss are jointly optimized to achieve robust de-raining performance and controllable model complexity. Extensive experimental results on both synthetic and realistic rainy images, as well as the down-stream vision applications (i.e., objection detection and segmentation) consistently demonstrate the superiority of our proposed method.