Fluorine- and Acid-Free Strategy toward Scalable Fabrication of Two-Dimensional MXenes for Sodium-Ion Batteries.

MXenes are emerging 2D materials that have gained great attention because of their unique physical-chemical properties. However, the wide application of MXenes is prohibited by their high cost and environmentally harmful synthesis process. Here a fluoride- and acid-free physical vacuum distillation strategy is proposed to directly synthesize a series of MXenes. Specifically, by introducing a low-boiling-point element into MAX and subsequently evaporating A elements via physical vacuum distillation, fluoride-free MXenes (Ti3C2Tx, Nb2CTx, Nb4C3Tx, Ta2CTx, Ti2NTx, Ti3CNTx, etc.) are fabricated. This is a green and one-step process without any acid/alkaline involved and with all reactions inside a vacuum tube furnace, avoiding any contamination to external environments. Besides, the synthetic temperature is controlled to regulate the layered structures and specific surface areas of MXenes. Accordingly, the synthesized Ti3C2Tx MXene exhibits improved sodium storage performance. This method may provide an alternative for the scalable production of MXenes and other 2D materials.

Robust-EQA: Robust Learning for Embodied Question Answering With Noisy Labels.

Embodied question answering (EQA) is a recently emerged research field in which an agent is asked to answer the user's questions by exploring the environment and collecting visual information. Plenty of researchers turn their attention to the EQA field due to its broad potential application areas, such as in-home robots, self-driven mobile, and personal assistants. High-level visual tasks, such as EQA, are susceptible to noisy inputs, because they have complex reasoning processes. Before the profits of the EQA field can be applied to practical applications, good robustness against label noise needs to be equipped. To tackle this problem, we propose a novel label noise-robust learning algorithm for the EQA task. First, a joint training co-regularization noise-robust learning method is proposed for noisy filtering of the visual question answering (VQA) module, which trains two parallel network branches by one loss function. Then, a two-stage hierarchical robust learning algorithm is proposed to filter out noisy navigation labels in both trajectory level and action level. Finally, by taking purified labels as inputs, a joint robust learning mechanism is given to coordinate the work of the whole EQA system. Empirical results demonstrate that, under extremely noisy environments (45% of noisy labels) and low-level noisy environments (20% of noisy labels), the robustness of deep learning models trained by our algorithm is superior to the existing EQA models in noisy environments.

From Global to Local: Multi-scale Out-of-distribution Detection.

Out-of-distribution (OOD) detection aims to detect "unknown" data whose labels have not been seen during the in-distribution (ID) training process. Recent progress in representation learning gives rise to distance-based OOD detection that recognizes inputs as ID/OOD according to their relative distances to the training data of ID classes. Previous approaches calculate pairwise distances relying only on global image representations, which can be sub-optimal as the inevitable background clutter and intra-class variation may drive image-level representations from the same ID class far apart in a given representation space. In this work, we overcome this challenge by proposing Multi-scale OOD DEtection (MODE), a first framework leveraging both global visual information and local region details of images to maximally benefit OOD detection. Specifically, we first find that existing models pretrained by off-the-shelf cross-entropy or contrastive losses are incompetent to capture valuable local representations for MODE, due to the scale-discrepancy between the ID training and OOD detection processes. To mitigate this issue and encourage locally discriminative representations in ID training, we propose Attention-based Local PropAgation (ALPA), a trainable objective that exploits a cross-attention mechanism to align and highlight the local regions of the target objects for pairwise examples. During test-time OOD detection, a Cross-Scale Decision (CSD) function is further devised on the most discriminative multi-scale representations to distinguish ID/OOD data more faithfully. We demonstrate the effectiveness and flexibility of MODE on several benchmarks - on average, MODE outperforms the previous state-of-the-art by up to 19.24% in FPR, 2.77% in AUROC. Code is available at https://github.com/JimZAI/MODE-OOD.

Hierarchical Co-Attention Propagation Network for Zero-Shot Video Object Segmentation.

Zero-shot video object segmentation (ZS-VOS) aims to segment foreground objects in a video sequence without prior knowledge of these objects. However, existing ZS-VOS methods often struggle to distinguish between foreground and background or to keep track of the foreground in complex scenarios. The common practice of introducing motion information, such as optical flow, can lead to overreliance on optical flow estimation. To address these challenges, we propose an encoder-decoder-based hierarchical co-attention propagation network (HCPN) capable of tracking and segmenting objects. Specifically, our model is built upon multiple collaborative evolutions of the parallel co-attention module (PCM) and the cross co-attention module (CCM). PCM captures common foreground regions among adjacent appearance and motion features, while CCM further exploits and fuses cross-modal motion features returned by PCM. Our method is progressively trained to achieve hierarchical spatio-temporal feature propagation across the entire video. Experimental results demonstrate that our HCPN outperforms all previous methods on public benchmarks, showcasing its effectiveness for ZS-VOS. Code and pre-trained model can be found at https://github.com/NUST-Machine-Intelligence-Laboratory/HCPN.

Hierarchical Graph Pattern Understanding for Zero-Shot Video Object Segmentation.

The optical flow guidance strategy is ideal for obtaining motion information of objects in the video. It is widely utilized in video segmentation tasks. However, existing optical flow-based methods have a significant dependency on optical flow, which results in poor performance when the optical flow estimation fails for a particular scene. The temporal consistency provided by the optical flow could be effectively supplemented by modeling in a structural form. This paper proposes a new hierarchical graph neural network (GNN) architecture, dubbed hierarchical graph pattern understanding (HGPU), for zero-shot video object segmentation (ZS-VOS). Inspired by the strong ability of GNNs in capturing structural relations, HGPU innovatively leverages motion cues (i.e., optical flow) to enhance the high-order representations from the neighbors of target frames. Specifically, a hierarchical graph pattern encoder with message aggregation is introduced to acquire different levels of motion and appearance features in a sequential manner. Furthermore, a decoder is designed for hierarchically parsing and understanding the transformed multi-modal contexts to achieve more accurate and robust results. HGPU achieves state-of-the-art performance on four publicly available benchmarks (DAVIS-16, YouTube-Objects, Long-Videos and DAVIS-17). Code and pre-trained model can be found at https://github.com/NUST-Machine-Intelligence-Laboratory/HGPU.

Highly Reversible Zn Metal Anodes Enabled by Freestanding, Lightweight, and Zincophilic MXene/Nanoporous Oxide Heterostructure Engineered Separator for Flexible Zn-MnO2 Batteries.

Aqueous zinc (Zn)-ion batteries are regarded as promising candidates for large-scale energy storage systems because of their high safety, low cost, and environmental benignity. However, the dendrite issue of Zn anode hinders their practical application. Herein, a freestanding, lightweight, and zincophilic MXene/nanoporous oxide heterostructure engineered separator is designed to stabilize a Zn metal anode. The nanoporous oxides prepared by a one-step vacuum distillation technique afford the advantages of large surface area, high porosity, and homogeneous porous structure. The zincophilic MXene@oxides layer can homogenize the electric field distribution, facilitate ion diffusion kinetics, reduce local current density, and promote even Zn ionic flux, which will regulate uniform Zn deposition and suppress side reactions. Accordingly, dendrite-free Zn anodes with stable cyclability are achieved for over 500 h at an ultrahigh area capacity of 10 mAh cm-2. Besides, flexible, long-lifespan, and high-rate N/S-doped three-dimensional MXene@MnO2||Zn full cells are constructed with the engineered separator. Moreover, this strategy can be successfully extended to lithium, sodium, potassium, and magnesium metal batteries, indicating that separator regulation is a universal approach to overcome the challenges of metal batteries.