Few-shot segmentation (FSS) has garnered significant attention. Many recent approaches attempt to introduce the segment anything model (SAM) to handle this task. With the strong generalization ability and rich object-specific extraction ability of the SAM model, such a solution shows great potential in FSS. However, the decoding process of SAM highly relies on accurate and explicit prompts, making previous approaches mainly focus on extracting prompts from the support set, which is insufficient to activate the generalization ability of SAM, and this design is easy to result in a biased decoding process when adapting to the unknown classes. In this work, we propose an unbiased semantic decoding (USD) strategy integrated with SAM, which extracts target information from both the support and query set simultaneously to perform consistent predictions guided by the semantics of the contrastive language-image pretraining (CLIP) model. Specifically, to enhance the unbiased semantic discrimination of SAM, we design two feature enhancement strategies that leverage the semantic alignment capability of CLIP to enrich the original SAM features, mainly including a global supplement at the image level to provide a generalize category indicate with support image and a local guidance at the pixel level to provide a useful target location with query image. Besides, to generate target-focused prompt embeddings, a learnable visual-text target prompt generator (VTPG) is proposed by interacting target text embeddings and clip visual features. Without requiring retraining of the vision foundation models, the features with semantic discrimination draw attention to the target region through the guidance of prompt with rich target information. Experiments on both the PASCAL- $5^{i}$ and COCO- $20^{i}$ show that our proposed method outperforms the existing approaches by a clear margin and achieves new state-of-the-art performances.

Training semantic segmenter with synthetic data has been attracting great attention due to its easy accessibility and huge quantities. Most previous methods focused on producing large-scale synthetic image-annotation samples and then training the segmenter with all of them. However, such a solution remains a main challenge in that the poor-quality samples are unavoidable, and using them to train the model will damage the training process. In this paper, we propose a training-free Synthetic Data Selection (SDS) strategy with CLIP to select high-quality samples for building a reliable synthetic dataset. Specifically, given massive synthetic image-annotation pairs, we first design a Perturbation-based CLIP Similarity (PCS) to measure the reliability of synthetic image, thus removing samples with low-quality images. Then we propose a class-balance Annotation Similarity Filter (ASF) by comparing the synthetic annotation with the response of CLIP to remove the samples related to low-quality annotations. The experimental results show that using our method significantly reduces the data size by half, while the trained segmenter achieves higher performance.

A tri-mode mixer supporting the 5G NR standards over 24.25--71GHz is presented. The harmonic-selection technique reduces the local oscillator (LO) frequency range and power consumption. Besides, the proposed multiphase LO rejects unwanted harmonics. Fabricated in a 65nm CMOS process, this work consumes 12-21mW power under a 1V supply. It presents more than 20dB rejections to the undesired harmonic components at all operation bands. The required LO frequency range is only 10GHz.

To meet the demand for high-speed and high-quality communication in next 6G satellite communication, it is very necessary and urgent to study the behavioral modeling of 6G satellite communication power amplifiers (PAs). In satellite communication, PAs face the situation of high dynamic and wide bandwidth and exhibit strong nonlinearity and strong memory effects. In this case, we need to study Transformer architectures that can better handle long sequence data and further explore the inherent characteristics of the PA signal data. In this article, we propose a behavioral modeling method of PAs named augmented real-valued time-delay transformer (ARVTDform). ARVTDform is an augmented transformer-based method, which can capture long-range dependencies between the PA signal data and has powerful nonlinear modeling capabilities. To simulate the working status of the satellite PAs, we set up two physical platforms and collect and analyze twelve datasets. To the best of our knowledge, this is the first time real satellite data has been used for behavioral modeling. Extensive experiments on the collected datasets further demonstrate that our transformer-based method is more suitable for handing PAs with strong nonlinearity and strong memory effects in terms of normalized mean square error (NMSE). Finally, we discuss the major challenge and list the potential future work that may contribute to the sustained development of high-performance transceivers.

In adverse environments, the detector often fails to detect degraded objects because they are almost invisible and their features are weakened by the environment. Common approaches involve image enhancement to support detection, but they inevitably introduce human-invisible noise that negatively impacts the detector. In this work, we propose a physics-guided approach for object detection in adverse environments, which gives a straightforward solution that injects the physical priors into the detector, enabling it to detect poorly visible objects. The physical priors, derived from the imaging mechanism and image property, include environment prior and frequency prior. The environment prior is generated from the physical model, e.g., the atmospheric model, which reflects the density of environmental noise. The frequency prior is explored based on an observation that the amplitude spectrum could highlight object regions from the background. The proposed two priors are complementary in principle. Furthermore, we present a physics-guided loss that incorporates a novel weight item, which is estimated by applying the membership function on physical priors and could capture the extent of degradation. By backpropagating the physics-guided loss, physics knowledge is injected into the detector to aid in locating degraded objects. We conduct experiments in synthetic foggy environment, real foggy environment, and real underwater scenario. The results demonstrate that our method is effective and achieves state-of-the-art performance. The code is available at https://github.com/PangJian123/See-Degraded-Objects.

Consistency learning is a central strategy to tackle unlabeled data in semi-supervised medical image segmentation (SSMIS), which enforces the model to produce consistent predictions under the perturbation. However, most current approaches solely focus on utilizing a specific single perturbation, which can only cope with limited cases, while employing multiple perturbations simultaneously is hard to guarantee the quality of consistency learning. In this paper, we propose an Adaptive Bidirectional Displacement (ABD) approach to solve the above challenge. Specifically, we first design a bidirectional patch displacement based on reliable prediction confidence for unlabeled data to generate new samples, which can effectively suppress uncontrollable regions and still retain the influence of input perturbations. Meanwhile, to enforce the model to learn the potentially uncontrollable content, a bidirectional displacement operation with inverse confidence is proposed for the labeled images, which generates samples with more unreliable information to facilitate model learning. Extensive experiments show that ABD achieves new state-of-the-art performances for SSMIS, significantly improving different base-lines. Source code is available at https://github.com/chy-upclABD.

Few-shot segmentation remains challenging due to the limitations of its labeling information for unseen classes. Most previous approaches rely on extracting high-level fea-ture maps from the frozen visual encoder to compute the pixel- wise similarity as a key prior guidance for the decoder. However, such a prior representation suffers from coarse granularity and poor generalization to new classes since these high-level feature maps have obvious category bias. In this work, we propose to replace the visual prior representation with the visual-text alignment capacity to capture more reliable guidance and enhance the model generalization. Specifically, we design two kinds of trainingfree prior information generation strategy that attempts to utilize the semantic alignment capability of the Contrastive Language-Image Pre-training model (CLIP) to locate the target class. Besides, to acquire more accurate prior guidance, we build a high-order relationship of attention maps and utilize it to refine the initial prior information. Experiments on both the PASCAL-5i and COCO-20i datasets show that our method obtains a clearly substantial improvement and reaches the new state-of-the-art performance. The code is available on the project website11https://github.com/vangjin/PI-CLIP.

This work first discusses the future directions of millimeter-wave wireless communication, based on Shannon and Friis equations. Afterward, 28-GHz and 39-GHz phased-array transceivers realized by 65nm CMOS technology are introduced, which are designed for 5G and beyond. The 28GHz phased- array transceiver is designed based on a neutralized bi-directional technique. The required chip area for the element transceiver is reduced to half. A cross-pol. leakage canceller is also implemented along with the transceiver to suppress the crosspol. leakage. Therefore, the dual-polarized 28-GHz phased-array module is capable to improve the wireless data with dual- polarized MIMO (DP-MIMO) configuration even under severe polarization coupling and rotation conditions. The measured DP-MIMO EVMs are 3.4% in both 64-QAM and 256-QAM. The 8-element 39GHz phased-array transceiver is also designed based on the compact bi-directional architecture. The Doherty technique is utilized in TX mode to increase the power efficiency at power backoff region. A 64-element transmitter array realizes a saturated output EIRP of 55.2dBm. To improve the phased- array performance under digital pre-distortion (DPD), an inter- element mismatch compensation technique is further employed. By utilizing the proposed mismatch compensation, the measured 64-QAM OFDMA-mode EVM and ACLR with the shared-look- up-table (shared-LUT) DPD are improved from -22.4dB to - 25.0dB and from -28.7dBc to -32.1dBc, respectively.

This paper presents high-accuracy phase and amplitude detection circuits for the calibration of 5G millimeter-wave phased array beamformer systems. The phase and amplitude detection circuits, which are implemented in a 65nm CMOS process, can realize phase and amplitude detections with RMS phase error of 0.17 degree and RMS gain error of 0.12 dB, respectively. The total power consumption of the circuits is 59mW.

A phase shifter with temperature compensation for 28GHz phased-array TRX is presented. A precise low-voltage current reference is proposed for the IDAC biasing circuit. The total gain variation for a single TX path including phase shifter and post stage amplifiers over -40°C to 80°C is only 1dB in measurement and the overall phase error due to temperature is less than 1 degree without off-chip calibration.

In a conventional domain adaptation person Re-identification (Re-ID) task, both the training and test images in target domain are collected under the sunny weather. However, in reality, the pedestrians to be retrieved may be obtained under severe weather conditions such as hazy, dusty and snowing, etc. This paper proposes a novel Interference Suppression Model (ISM) to deal with the interference caused by the hazy weather in domain adaptation person Re-ID. A teacher-student model is used in the ISM to distill the interference information at the feature level by reducing the discrepancy between the clear and the hazy intrinsic similarity matrix. Furthermore, in the distribution level, the extra discriminator is introduced to assist the student model make the interference feature distribution more clear. The experimental results show that the proposed method achieves the superior performance on two synthetic datasets than the state-of-the-art methods. The related code will be released online https://github.com/pangjian123/ISM-ReID.

In this paper, a fully-synthesizable digital-to-time (DTC)-based fractional-Nmultiplying delay-locked loop(MDLL) is presented. Noise and linearity of synthesizable DTCs are analyzed, and a two-stage synthesizable DTC is proposed in which a path-selection DTC is used as the coarse stage and a variable-slope DTC is used as the fine stage. To calibrate the DTC nonlinearity, a highly robust zero-order interpolation based nonlinearity calibration is proposed. Besides, the static phase offsets (SPO) between bang-bang phase detector (BBPD) and multiplexer (MUX) are calibrated by a proposed hybrid analog/digital phase offset calibration, while the dynamic phase offsets (DPO) are removed by a proposed complementary switching scheme. The co-design of the analog circuits and digital calibrations enable excellent jitter and spur performance. The MDLL achieves 0.70 and 0.48ps root-mean-square (RMS) jitter in fractional-N and integer-N modes, respectively. The fractional spur is less than -59.0dBc, and the reference spur is -64.5dBc. The power consumptions are 1.85mW and 1.22mW, corresponding to figures of merit (FOM) of -240.4dB and -245.5dB.

This article presents a small-area Bluetooth Low-Energy (BLE) transceiver (TRX) for short-range Internet-of-Things (IoT) applications in 65-nm CMOS. An integrated Radio-Frequency Input-Output (RFIO) circuitry embedded with transmitter/receiver (TX/RX) switch function and on-chip impedance matching is proposed. A hybrid-loop TRX structure based on a wide-bandwidth fractional-N digital phase-locked loop (DPLL) is implemented to achieve the maximum power reduction. A -94dBm receiver sensitivity is achieved with 2.3mW receiver power consumption, while a RF receiving bypass route integration enhances the input power tolerance. The BLE transceiver delivers -6dBm output power while consuming 2.6mW and delivers 0dBm output power while achieving 18.5% maximum TX efficiency. Thanks to the RFIO with harmonic suppression, -56dBc of 2nd-order harmonic distortion (HD2) and -48dBc of 3rd-order harmonic distortion (HD3) suppression are achieved with 0.85mm2on-chip area. This transceiver satisfied the BLE radio specification without the need for external filters and with low-power consumption, which enables minimum size and long life-time modules.

A 28GHz differential bi-directional amplifier in a standard 65nm CMOS process is presented. This work is realized based on the neutralized bi-directional core together with the fully shared inter-stage matching networks. The core chip area is only 0.11mm2. At 28GHz, a 15.1-dBm saturation output power and a 4.2-dB noise Figure are realized for PA mode and LNA mode, respectively. The DC power consumptions for PA mode and LNA mode are 149mW and 31mW, respectively, under 1-V DC supply.